Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: ordered execution, halt-on-first-failure (consistent with idempotentHint=false, since partial application is non-repeating), per-step snapshot/journal creation, the confirmationToken requirement for non-admin callers, and the rollback path. Nothing contradicts the destructiveHint/readOnlyHint declarations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, zero filler, ordered by importance: what execution means, how it's journaled, then the auth requirement and undo path. Every clause carries operational information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive batch tool with no output schema, the description covers the essentials: sequencing, failure behavior, auth prerequisites, and where the returned journal IDs go. It even hints at the return value (journal IDs) that the absent output schema would otherwise hide.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67%, and the schema already documents steps, its item shape and the routerId default. The description adds the key semantic that confirmationToken is a non-admin requirement, but the token's acquisition flow and routerId's effect are left to the schema. Adequate but not compensatory.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: it executes an ordered batch of write operations. The failure semantics ('stopping on first failure') and per-step journaling make the operation concrete. It doesn't explicitly differentiate itself from siblings like plan_changes or bulk_execute, so an agent must infer the preview-then-apply relationship.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real usage conditions: non-admin identities need a confirmationToken, and individual steps are undone via rollback_change. The phrase 'same two-step flow as other destructive tools' signals prior token acquisition. What's missing is an explicit statement that plan_changes should be called first to preview the plan.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare destructive/idempotent; the description adds the write ordering (VLANs first, table shrink last), the full list of lockout-risk conditions, the six-endpoint snapshot before a real apply, the rollback_change recovery path, the management-change refusal, the safe-order refusal for management moves, and the secrets binding rule for snmp.community.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single dense paragraph, but it is front-loaded with the core action and the dryRun default, and the chronological ordering gives it structure. Nearly every clause carries a distinct rule, so the length is justified by the tool's complexity, though the run-on semicolon chains hurt scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a high-risk, 7-parameter tool with no output schema, the description covers the missing surface: result reporting on snapshot failures, refusal conditions, secret scoping, ordering constraints, and the rollback path. An agent has everything needed to call it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description adds real meaning: the dryRun default, the refusal semantics behind includeManagement/acceptLockoutRisk, the confirmationToken approval flow, and that pruning/table shrink is tied to the vlans list. The parameter-to-behavior mapping is clearer here than in the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Apply a switch config document (the format get_swos_config exports) to a SwOS switch.' It ties itself to its siblings get_swos_config (producer of the format) and rollback_change (which reverses it), so an agent can distinguish it without opening another schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-it-refuses: dryRun defaults to true, includeManagement gates management changes, acceptLockoutRisk gates plans that cut off linked ports, and confirmationToken handles the APPROVAL_REQUIRED flow. It even gives ordering advice for the multi-step management-move case ('apply the VLAN changes first, then the move').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include readOnlyHint=true and destructiveHint=false, but the description adds critical context: the test saturates the link and is not auto-retried. This goes beyond the annotations, which already indicate safe behavior, to warn about real-world impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is just two sentences. The first sentence states purpose and output, the second adds key constraints and warnings. Every word is necessary; no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description correctly includes return format. It covers the main behavioral traits (duration cap, link saturation, no retry). However, it does not mention error cases (e.g., if the remote host is not running a btest server). For a simple diagnostic tool, this is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 5 parameters are documented in the schema (100% coverage). The description adds value by specifying that the tool returns TX and RX throughput in Mbps, which is not present in the input schema. No further parameter details are needed beyond what schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool runs a RouterOS bandwidth test, specifies it tests from router to a remote host running a btest server, and returns TX/RX throughput. It distinguishes itself from sibling diagnostic tools like ping, traceroute, and torch by focusing specifically on bandwidth testing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context about duration cap and link saturation, implying careful use, but does not explicitly state when to use vs. alternatives (e.g., ping for latency, traceroute for path). No exclusions or when-not-to-use guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive=true/readOnly=false, but the description adds substantial context beyond them: the two-step fleet confirmation token flow, snapshot+journal per-router rollback, and the shape of the response (succeeded/failed counts). These are exactly the mutation-safety details an agent needs and that the annotations do not carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action, then sequences confirmation, rollback, return, and the alternative routing in tight sentences. Every sentence carries distinct information with no restatement of the name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, multi-target tool with no output schema, the description covers the targeting model, the confirmation requirement, rollback behavior, and return summary. Nothing an agent needs in order to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by framing concurrency as the parallel fan-out cap, clarifying that targeting is by routerIds or tag, and explaining the confirmationToken round-trip. It does not add format/syntax beyond the schema, so it sits just above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('fan out a single-router tool to many routers in parallel') and immediately bounds it ('targeted by routerIds or tag'). It explicitly names the sibling it is not for read-only cases ('prefer bulk_read'), so an agent can distinguish it without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use routing ('To fan out a read-only tool, prefer bulk_read') plus the write-path workflow (call without confirmationToken to get a fleet token, then re-call). The read-vs-write selection condition is fully spelled out with no inference required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the specific BULK_READ_TOOL_NOT_READ_ONLY rejection code, the fact that no confirmation token, snapshot or journal is required, and the security rationale (an MCP client can allow it without allowing fleet-wide writes). This is exactly the extra behavioral disclosure expected when annotations carry the safety baseline.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded in the first clause, and the long second sentence is dense but each clause (refusals, no token, security implication, alternative) earns its place. Slightly overlong for a single block, but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a fan-out tool with no output schema, the description covers the essential concerns: targeting, parallelism, refusal semantics, and return shape (per-router results with succeeded/failed counts). Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so toolName, params, routerIds, tags and concurrency are all documented in the schema. The description echoes targeting by routerIds or tag and the concurrency cap but adds no syntax or format detail beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action and resource: fan out a read-only single-router tool to many routers in parallel, and names the two targeting modes (routerIds or tag). It explicitly contrasts with the sibling bulk_execute, so an agent can distinguish the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit routing: use bulk_execute for anything else, and enumerates what bulk_read will refuse (write tools, ping, traceroute, torch, bandwidth_test). The when-to-use and when-not-to-use conditions are both spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds valuable behavioral context: 'never throws' and the unreachable-device handling (reported as healthy=false), plus the distinction between RouterOS and SwOS. This goes beyond annotations without contradiction, though it doesn't cover auth or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with the primary action, and every clause adds value (device types, return fields, and the non-throwing behavior). No redundancy or fluff; it is efficiently structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one optional parameter and no output schema, the description sufficiently covers what the tool does, what it returns, and its failure mode. It also clarifies platform-specific differences in returned data, making it complete for the given complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% since the only parameter, routerId, has a clear description ('Router ID; omit to use the default router'). The description does not add any additional semantics beyond the schema, matching the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: 'Probe a device' with specific protocols (system/resource, sys.b) and explicitly lists the returned fields (health status, firmware version, uptime, CPU load, memory info). It distinguishes itself from siblings by mentioning 'Unlike other tools, this never throws,' making its unique behavior clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage via 'Probe a device' and its focus on health, but it does not explicitly state when to use this tool over alternatives, nor does it name specific sibling tools. The 'Unlike other tools' hint suggests robustness as a differentiator, but exclusions or alternative recommendations are absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavior: the artifact lands as <name>.backup on the router filesystem and dry run only validates secret resolution rather than creating anything — context the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no filler: the action, the output artifact, then the encryption preference with dry-run behavior. The most decision-critical constraint (secret over literal password) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive zero-required-param mutation with a fully documented schema and no output schema, this is nearly complete. The one gap is that it doesn't flag overwrite risk if <name>.backup already exists on the router filesystem, which matters for a destructive tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description still adds decision-relevant semantics by stating a preference ordering between password and passwordSecret and explaining that the secret value never enters the conversation, which is more than the per-field descriptions convey on their own.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Create a binary configuration backup on a MikroTik router') plus the resulting file name, which is far more concrete than a tautology. It does not explicitly differentiate itself from siblings like export_config or save_swos_backup, which is the only thing keeping it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives useful in-tool guidance — prefer passwordSecret over a literal password, and dry run verifies the secret resolves. It never says when to pick this over export_config (textual export) or save_swos_backup, so sibling-level routing is left implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond annotations by stating 'returns not_found gracefully if the file does not exist.' Annotations already provide destructiveHint=true and idempotentHint=true, so the description elaborates on the idempotent behavior. However, it could mention permission requirements or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences, front-loading the key action ('Delete a file...'). No redundant information, and each sentence serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 4 parameters including dryRun and confirmationToken, the description does not explain their purpose or the approval flow. Since there is no output schema, the description should hint at return values. The tool is destructive, so missing context on confirmation token undermines safe usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already documents each parameter (routerId, name, dryRun, confirmationToken). The tool description adds no additional meaning beyond the schema, meeting the baseline expectation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Delete a file from the router filesystem by name.' It uses a specific verb ('Delete') and resource ('file'), distinguishing it from sibling tools like upload_file, list_files, and manage_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The description mentions idempotency and graceful handling of non-existent files, but does not provide context for when deletion is appropriate or when to prefer other tools (e.g., backup before delete).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive=true, idempotent=true, readOnly=false, so the safety profile is covered. The description adds genuinely new behavioral context: the file is written as <file>.rsc on the router filesystem, and the no-file path returns inline text, which tells the agent what side effect to expect. It does not mention the approval/confirmation flow, though the schema parameter covers that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with purpose and then the two conditional behaviors; no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully explains the return format (inline script text vs file on disk), which is what an agent most needs here. It omits any mention of the destructive-action confirmation requirement, but that is documented on the confirmationToken parameter, so the gap is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by naming the exact artifact created (<file>.rsc) and restating that compact mode filters to non-default values, resolving ambiguity about what 'compact' produces.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (export) and resource (router configuration) plus the output format (RouterOS script), so the agent knows exactly what it produces. It does not distinguish itself from adjacent tools like create_backup or get_file_content, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains the two operating modes (no file = inline text, file = saved to disk), which implies when each is appropriate, but it never explicitly says when to use this tool versus create_backup or how to read the saved file afterward.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already supply readOnlyHint=false, destructiveHint=true, and idempotentHint=false. The description adds genuine context beyond them: the 64 KB response cap with a [TRUNCATED] marker, and the reasons for the write profile (POST side effects, outputFile writes). This enriches rather than merely repeats the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences, front-loaded with the core action and followed by return behavior and the write caveat. No filler; each sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema present, the description carries the return-value burden and does so by explaining the inline body, its 64 KB cap, and truncation. The confirmationToken approval flow is left entirely to the schema, leaving a small gap for a destructive tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters including outputFile's inline-vs-file behavior. The description adds only marginal parameter meaning (the truncation limit tied to inline returns), so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Send an HTTP/HTTPS request from the router using /tool/fetch') with concrete scope. It is a unique capability in the sibling set, and an agent can identify exactly what it does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear conditional guidance on output handling ('Use outputFile to save to router filesystem instead'), helping the agent choose between inline return and file storage. It does not name alternative tools, but no sibling competes for this function, so context is adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, non-destructive, and idempotent behavior. The description confirms the read operation and lists specific fields returned, adding some context but not elaborating on other behavioral traits like permissions or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single 12-word sentence that is front-loaded and contains no unnecessary words. Every part is informative and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with one optional parameter, the description is fairly complete. It lists the specific configuration items returned. Minor omission: does not clarify behavior when routerId is omitted vs provided, but the schema param description covers that. Output schema is absent but the description mitigates it by listing fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with a clear description for the optional 'routerId' parameter. The description does not need to add further parameter details, and the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Read' and specifies the resource 'global container configuration' along with exact items (registry URL, RAM high-water mark, veth interface). This distinguishes it from write siblings like manage_container_config.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for reading configuration but does not explicitly state when to use this tool versus alternatives (e.g., manage_container_config for modifications). No exclusions or when-not-to-use guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, indicating a safe, read-only, idempotent operation. The description adds context by enumerating exactly what configuration fields are read (upstream servers, cache size, etc.), which goes beyond the annotation metadata and helps the agent understand the return content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that begins with the imperative verb 'Read' and immediately states the resource. Every word serves a purpose, with no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with one optional parameter and no output schema, the description is fairly complete. It lists all major fields that would be returned. However, it lacks details about potential error conditions or the exact structure of the response, but it is sufficient given the tool's low complexity and the presence of supportive annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single optional parameter 'routerId', which the schema describes as 'Router ID; omit to use the default router.' The description does not add any additional meaning about this parameter beyond what the schema already provides. Since coverage is high, a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads DNS resolver configuration and lists specific attributes: upstream servers, cache size, cache TTL, and remote DNS request allowance. It uses a specific verb ('Read') and resource ('DNS resolver configuration'), and is easily distinguishable from sibling tools like manage_dns_settings (write) and get_ntp_settings (different resource).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. It does not mention that manage_dns_settings is used for modifications, nor does it specify any prerequisites or restrictions (e.g., router context). The agent must infer usage from the 'Read' verb alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate read-only and idempotent behavior. The description adds a critical behavioral note about binary files causing garbled output, which is not captured in structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no extraneous information. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so the description could specify return format (e.g., plain text). However, given the simple read operation and rich annotations, the current description is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and parameter descriptions are adequate. The description does not add new meaning beyond the schema, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Read a text file's contents from a MikroTik router,' providing a specific verb and resource. It effectively distinguishes from sibling tools like upload_file or delete_file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly warns that binary files return garbled content, guiding the agent to use this tool only for text files. Does not name alternative tools for binary files, but the guidance is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral details: time window measured against router's clock and conservative inclusion of unparseable timestamps, which go beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences, with the first sentence delivering the core purpose and the second adding key features and an edge case. Every word serves a purpose; no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 6 optional parameters and no output schema, the description covers main filtering options and an edge case. It lacks detail on return format, but the tool's name and purpose imply a list of log entries; sufficient for a read operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All parameters have descriptions in the schema (100% coverage). The description only summarizes filtering by topic, prefix, and time window, adding no new details beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the verb 'Read and filter' and the resource 'system log from a MikroTik router'. It distinguishes the tool from sibling list tools by focusing on log reading with filtering capabilities, leaving no ambiguity about its purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description outlines supported filters (topic, prefix, time window), implying when to use the tool (e.g., when logs need filtering). However, it does not explicitly state when not to use it or suggest alternatives, though no direct sibling conflict exists.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint. The description adds only generic context ('from a MikroTik router') without additional behavioral details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One concise sentence that conveys the core purpose without unnecessary words, well front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple retrieval tool with no output schema, the description adequately covers what the tool does, though it could specify what 'NTP client settings' includes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter 'routerId' is already described in the schema. The description adds no further parameter information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Retrieve') and resource ('NTP client settings') and clearly distinguishes from sibling tools like 'manage_ntp_client' which suggests mutation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives, though the purpose is clear from the name and context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate safe, read-only, idempotent behavior. The description adds value by disclosing that a NOT_FOUND error occurs if the OpenVPN package is missing, which is not covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, front-loaded with the main action, and contains no redundant or irrelevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with good annotations, the description covers the core purpose and one key error. However, it could mention the return format or additional error cases for completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a clear description for the single optional parameter (routerId). The tool description does not add extra parameter meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves OpenVPN server configuration on a MikroTik router, with a specific error condition. It distinguishes from siblings like manage_ovpn_server (modification) and list_ovpn_clients (client list).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The verb 'Get' and readOnlyHint imply read-only usage, and the description mentions an error condition (NOT_FOUND). However, it does not explicitly state when to avoid using it or name alternatives for write operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate the tool is read-only, non-destructive, idempotent, and has a closed world. The description adds minimal behavioral context beyond stating the resource type and source device. It does not contradict annotations but also does not disclose any additional behaviors or constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no unnecessary words. It is front-loaded and immediately conveys the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (one optional parameter, no output schema, no nested objects), the description is minimally adequate. However, it lacks details about which specific SNMP settings are returned or any format expectations, which would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with the single optional parameter well-documented in the schema. The description adds no additional meaning about parameters beyond what the schema provides, so the baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Retrieve', the resource 'SNMP settings', and the target 'MikroTik router'. It distinctly identifies the tool's function and differentiates it from sibling tools like get_dns_settings or get_ntp_settings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, typical usage scenarios, or when to prefer other tools for similar purposes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover safety (read-only, idempotent, non-destructive), and the description adds substantive behavior: exact export contents, the explicit exclusion of the SNMP community, and the YAML output relationship to apply_swos_config. This goes well beyond the structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences, front-loaded with the action and output format, followed by contents, exclusion, and relationship to the apply tool. Every sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only export tool with no output schema, the description explains the return document's contents and its role as apply_swos_config input. Annotations cover safety and the schema covers the only parameter, leaving no material gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the sole parameter routerId is documented in the schema with default-router behavior. The description adds no additional parameter meaning, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Export) and resource (SwOS switch configuration) plus the output format (YAML). It enumerates contents and names the related sibling apply_swos_config, letting an agent distinguish it from status/backup tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clearly positions the tool as a read/diff backup and as the input format for apply_swos_config, which tells the agent when it is useful. It does not explicitly exclude alternatives such as save_swos_backup, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only, idempotent, non-destructive profile. The description adds a valuable behavioral detail: unknown keys are preserved under '_raw', which tells the agent how to handle unexpected fields. It does not mention authentication or error behavior, but given the annotation coverage this is a solid addition.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the first front-loads the purpose with examples, the second adds a key behavioral note. No filler or redundancy, every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with 100% schema coverage, rich annotations, and no output schema, the description covers what the tool does and a key behavior (_raw). Nothing critical is missing for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are documented in the schema. The description lists many endpoint examples, but this largely duplicates the enum and adds no syntax or semantic detail beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Fetch and decode') and resource ('a single SwOS '.b' endpoint') with examples, and the word 'single' implicitly distinguishes it from list_swos_endpoints. However, it does not explicitly name the sibling or contrast it with get_swos_config or other SwOS tools, so it falls short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (fetch one endpoint's structured data) but provides no explicit when-to-use, when-not-to-use, or alternative tool guidance. An agent must infer that list_swos_endpoints is for listing and this is for retrieving a specific endpoint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds a compatibility constraint ('SwOS or SwOS Lite') and lists return content, but does not disclose deeper behavior like multiple HTTP requests, failure modes, or return format. This is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense sentence that leads with the action and resource, then compacts the full scope into a list. Every clause contributes meaning; no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only status tool with two well-documented parameters and strong annotations, the description is largely complete. It lists the returned data categories, making up for the lack of an output schema. It could have mentioned the include parameter's default behavior or the distinction from get_swos_endpoint, but these are minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining what the cryptic enum values ('link.b', 'sys.b', 'poe.b', 'sfp.b') actually return: link state/speed/duplex, system identity/model/uptime, PoE details, and SFP modules. This maps directly to the include parameter, exceeding the schema's minimal 'Which status endpoints to fetch'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Retrieve') and a clear resource ('status from a MikroTik SwOS switch'), then enumerates the exact data categories: identity, model, firmware, uptime, per-port link state, PoE, and SFP modules. This distinguishes it from siblings like get_system_status (RouterOS status) and get_swos_endpoint (raw endpoint retrieval).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: it should be used when you need switch status information from a SwOS/SwOS Lite device. However, it provides no explicit when-to-use guidance, exclusions, or alternatives, such as noting that get_swos_endpoint is for raw endpoint data.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds that it reads the clock, but no further behavioral details are provided. With annotations covering the safety profile, a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with no wasted words. It is front-loaded with the purpose and immediately provides distinguishing context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with good annotations, the description is complete enough. It does not specify return values, but given the straightforward nature of the tool, this is not a major gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage for the single optional parameter (routerId). The description does not add additional semantics beyond the schema's parameter description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it reads date/time/timezone from a MikroTik router. It distinguishes itself from get_system_status by being a focused single-purpose alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description positions it as an alternative to the clock section in get_system_status, providing usage context. However, it does not explicitly state when not to use it or list other alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds context about the variety of data sections retrievable (e.g., health, clock) and mentions the routerId parameter. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that efficiently conveys the tool's purpose and scope. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 2 parameters fully described, no output schema, and annotations confirming safety, the description is adequate. However, it lacks any description of the output format or structure, which would be helpful for an agent to interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters (routerId, sections) having clear descriptions and enums. The description's mention of 'resource usage, identity, license, routerboard details, health sensors, and clock' maps directly to the sections enum, but adds no new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Retrieve' and resource 'system status' with a specific list of included sections (resource usage, identity, license, routerboard details, health sensors, clock). This distinguishes it from sibling tools like get_system_clock, which only returns clock info.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving broad system status but does not explicitly provide when-to-use or when-not-to-use guidance. Given many sibling tools that retrieve specific status pieces, it would benefit from stating that this is a comprehensive overview.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds value by specifying the exact information returned (versions, channel, firmware availability), enhancing transparency beyond the annotations. No contradictions. A slight deduction because the description doesn't mention any side effects (though none exist).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with the key action and resource. No unnecessary words. Highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple with one optional parameter and no output schema. Description fully explains the return values and covers all necessary context. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (both properties described). The description does not add any additional meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verb 'Read' and identifies the resource as 'RouterOS package upgrade status and routerboard firmware versions'. It lists concrete output fields (installed version, latest available, update channel, firmware upgrade availability), making its purpose crystal clear and distinguishing it from siblings like 'manage_upgrade' which perform modifications.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit 'when to use' or alternative guidance, but the name and description strongly imply it is for pre-upgrade checks. The sibling tool 'manage_upgrade' exists, suggesting this is for read-only status. A score of 4 reflects clear implicit usage without explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so description does not need to reiterate safety. It adds filtering context but no additional behavioral details beyond schema. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose and includes key detail (filtering) without superfluous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity as a read-only list operation with three optional parameters and no output schema, the description sufficiently covers the functionality. Slight gap: no mention of return format or ordering, but not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing clear definitions for all three parameters. The description merely repeats the filtering capability, adding no new meaning beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and the resource 'firewall address list entries', and distinguishes it from sibling tools like 'manage_address_list_entry' by focusing on listing. The mention of filtering adds specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates when to use the tool (to list entries with filtering options) but does not explicitly state when not to use it or suggest alternatives among siblings, though context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds no behavioral details beyond that, such as pagination, performance impact, or rate limits. It fails to disclose any hidden behaviors.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at 8 words, single sentence, no redundant information. Every word is meaningful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description provides the basic purpose but omits details like the return format, default router behavior, or that filters use substring matching. For a simple list tool with full schema coverage, it is adequate but not thorough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description does not add any additional meaning beyond the schema descriptions. Parameters are adequately documented in the schema itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists ARP table entries on a MikroTik router. It is specific about the resource (ARP entries) and the action (list), and distinguishes it from other list tools by naming the resource type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like list_neighbors or address list tools. The description lacks context for when filtering by interface/address/mac is appropriate, and does not mention when to avoid using it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, indicating safe read-only behavior. The description adds useful context: target RouterOS version 7+ and specific returned fields, enhancing transparency beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence that front-loads the purpose and returns, with no wasted words. It efficiently conveys the necessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description provides sufficient context by listing return fields. It covers the core functionality, though missing details like default router behavior or error handling. Still, it is largely complete for a simple list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers both parameters with descriptions, achieving 100% coverage. The description adds examples of allowed state values (established, active, idle) but does not significantly add meaning beyond the schema. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists BGP sessions on a specific platform (MikroTik RouterOS 7+), with explicit mention of returned fields (state, remote AS, prefix counts, uptime). This distinguishes it from sibling list tools like list_ospf_neighbors or list_ipsec_peers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives (e.g., list_ospf_neighbors). Usage is implied by the purpose (BGP sessions), but no exclusions or context for when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world). The description adds useful context by naming the entry fields returned (interface membership, PVID, STP role/status) and noting filtering/pagination support, though it does not discuss auth or pagination behavior in depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly written sentences: the core purpose and returned fields come first, followed by filtering/pagination capabilities. There is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given full schema documentation, safe read-only annotations, and no output schema, the description supplies enough context to call the tool correctly, including what entries contain and that filtering/pagination exist. Minor omissions like default router behavior are already covered by the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the input schema. The description only generically mentions filtering by bridge/interface and pagination, adding no syntax or format meaning beyond what the schema provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb (List), resource (bridge port entries), platform (MikroTik router), and even enumerates the returned fields. It clearly distinguishes this read-only listing from sibling tools like manage_bridge_port and list_bridges.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it by stating it lists bridge port entries and supports filtering by bridge/interface, but it never explicitly contrasts usage with siblings such as manage_bridge_port, list_bridges, or list_interfaces. This is adequate but leaves routing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, non-destructive, idempotent. Description adds that port members are included, but no additional behavioral details (e.g., pagination behavior, performance characteristics). Value added beyond annotations is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence of 14 words, front-loaded with the verb 'List'. No unnecessary words or repetition. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and high schema coverage, the description is complete enough. It states what the tool returns (bridge interfaces and port members), which is sufficient for an agent to decide to invoke it. No output schema, but the implied return structure is clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers all 3 parameters (routerId, limit, offset) with descriptions. Description does not add further meaning beyond what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action (List) and resource (bridge interfaces and their port members). It differentiates from sibling tools like 'list_interfaces' or 'manage_bridge' by specifying both the resource and the scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use or when not to use this tool over alternatives. The name and description imply it's for retrieving bridge interface information, but no alternatives or exclusions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description does not add behavioral context beyond annotations (readOnlyHint=true, idempotentHint=true). It is truthful but shallow; no mention of filtering behavior or results handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence, no wasted words. However, the simplicity suits a list tool and information density is adequate.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description does not explain return values. Annotations cover safety, but for a list tool, describing the result format would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Parameter descriptions in the input schema are complete (100% coverage). The tool description adds no new meaning, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List certificates on a MikroTik router' with a specific verb and resource. It distinguishes the tool from siblings like list_files or list_interfaces, but does not elaborate on scope or differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. Despite many sibling list tools, the description offers no context for selection or exclusion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (readOnlyHint: true, destructiveHint: false, idempotentHint: true) indicate a safe, read-only operation. The description adds that 'Filters are applied client-side,' which is crucial behavioral context not present in annotations, informing the agent about performance and data handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of two sentences that cover purpose, source, filter behavior, and use case. Every word serves a purpose; no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 5 parameters, all documented in schema, and no output schema, the description covers the main function and filter behavior. It does not specify the return format (e.g., list of objects with fields), but for a simple list tool with read-only hints, this is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents each parameter. The description adds limited value beyond the schema, only mentioning that filters are client-side, which is a general observation. No specific parameter meanings are elaborated beyond what's in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (list) and the resource (active connection tracking entries from the router firewall table). This distinguishes it from many sibling list_* tools that target different resources (e.g., list_firewall_rules, list_interfaces).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the tool is 'useful for diagnosing NAT and firewall behavior,' providing a clear use case. It does not explicitly state when not to use it or list alternatives, but the context is adequate given the sibling list of many specialized tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds the filtering behavior, but overall adds little beyond the annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, 8 words, front-loaded with action and resource. Every word is necessary; no wasted text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with complete schema descriptions and informative annotations, the description is sufficient. No output schema is present, but the tool's purpose is straightforward. Could briefly note that entries are key-value pairs, but not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters have descriptions in the input schema (100% coverage). The description does not add new meaning beyond repeating the filtering capability. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (list), resource (container environment variable entries), and optional filtering by container name. It distinguishes itself from siblings like list_containers or manage_container_env.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for reading env entries, optionally filtered, but does not explicitly state when to use this tool vs alternatives like manage_container_env (which modifies). No when-not or exclusions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description carries minimal burden. It adds no new behavioral details (e.g., pagination, permissions, default router behavior), which is acceptable but not exemplary.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no extraneous words. It efficiently communicates purpose and output details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list query with three optional parameters and no output schema, the description is largely sufficient. It specifies returned fields. Minor omission: behavior when routerId is omitted (default router) is in schema, not description, but that's acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already described. The description adds value by specifying the output fields (source path, destination path, mount name), which aids in tool selection beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists container volume mount definitions and specifies the returned fields (source path, destination path, mount name). It distinguishes itself from sibling tools like manage_container_mount (which modifies mounts) and list_containers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly provide when-to-use or when-not-to-use guidance. It implies a read-only query, but lacks mention of alternatives or exclusions. However, the context of sibling tools makes usage inferable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the tool as readOnly (readOnlyHint=true), non-destructive, and idempotent. The description adds no behavioral context beyond these annotations, such as authorization needs or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that is front-loaded with the core purpose. No wasteful words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description provides basic purpose but lacks details on output format, pagination, or behavior when routerId is omitted. Given the simplicity and absence of output schema, it is adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the only parameter (routerId). The description does not add any additional meaning or usage guidance for the parameter, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists RouterOS container instances with specific details (status, image, network information). It uses a specific verb 'List' and resource, and distinguishes from sibling list_* tools for other resource types.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance is provided. However, the name and description imply it is for listing containers, and siblings cover other resources, so usage is straightforward.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds the useful detail that output includes interface, DHCP status, and assigned address, but says nothing about pagination defaults, result ordering, or the default-router behavior when routerId is omitted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and resource, with zero filler. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only list tool with annotated safety, fully documented parameters, and no output schema, the description is nearly complete: it covers the resource and the shape of the returned data. The only gap is that it doesn't hint at pagination scaling or how status/interface filters interact with the results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters (limit, offset, status, routerId, interface) are fully documented in the schema. The description adds no parameter-level meaning beyond what the schema already provides; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (list) and resource (DHCP client configurations) on MikroTik, and the second sentence explains what data those configurations expose. It is distinguishable from list_dhcp_servers/list_dhcp_leases by the word 'client', though it never names the siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit when-to-use or when-not-to-use guidance, and no routing to alternatives such as manage_dhcp_client for mutations or list_dhcp_leases for server-side leases. Usage is only inferable from the tool name and read-only annotations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is fully consistent with annotations (readOnlyHint, destructiveHint, idempotentHint). It adds context about filtering and pagination behavior, which complements the annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that front-loads the core function and lists key capabilities. Every word adds value; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and the rich schema, the description is complete. It mentions pagination (important for listing tools) and all filter options. No output schema is needed as the return format is implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good descriptions for all 7 parameters. The description briefly mentions the filter options but adds no significant semantic value beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists DHCP leases on a MikroTik router, with optional filtering by server, status, type, and MAC address, and supports pagination. It is specific and distinguishes it from sibling tools like 'list_dhcp_clients' and 'manage_dhcp_lease'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it (to view leases with optional filters) but does not explicitly mention when not to use it or suggest alternatives like 'manage_dhcp_lease' for modifications. The context is clear enough for a read-only list tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, fully describing the safety profile. The description adds no extra behavioral details beyond the obvious listing operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence of six words. Every word is necessary and there is no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a simple list operation with no output schema, so the description is nearly complete. A minor improvement could be mentioning pagination or default router behavior, but it is adequate as is.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with all parameters documented. The description does not add any semantic beyond what the schema already provides, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (List), the resource (DHCP servers), and the scope (on a MikroTik router). It is specific and distinguishes from sibling tools like list_dhcp_clients and list_dhcp_leases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, such as manage_dhcp_server for configuration. No situational context is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds the specificity of 'static DNS entries' (implying non-dynamic records) and optional filtering, which is consistent and adds value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys the core purpose and filtering capability without any fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lacks mention of return values (e.g., list of matching entries or empty response) or behavior for edge cases. Given the absence of an output schema, this information would help complete the context, though the description is minimally sufficient for a list operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with each parameter having clear descriptions. The tool description only mirrors 'optional filtering by name and type' without adding new semantics or context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'List' and the resource 'static DNS entries on a MikroTik router' with optional filtering. It distinguishes itself from sibling list tools by specifying the DNS entry type and from manage_dns_entry which handles modifications.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. While it mentions filtering, it does not explain when list_dns_entries is preferred over manage_dns_entry or other list tools for different DNS scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, non-destructive, and idempotent behavior. The description adds no significant behavioral context beyond 'list files,' which is consistent with annotations but does not address aspects like completeness or ordering of results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero waste. Front-loaded with core purpose, followed by filtering capabilities. No unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Meets minimal needs for a simple list tool with optional filters. Minor ambiguity about filter behavior (substring vs exact) and no mention of return format, but adequate given annotations cover safety and idempotency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions. The description reiterates filtering by name and type but adds no semantics beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists files on a MikroTik router filesystem, with specific filtering support, distinguishing it from sibling list tools (e.g., list_interfaces, list_scripts) by explicitly naming the resource type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide guidance on when to use this tool versus alternatives like get_file_content or delete_file, nor does it mention prerequisites or context. However, the purpose is straightforward for a list operation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds that it supports filtering and pagination, which is consistent. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded with purpose and followed by capabilities. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, and the description does not describe the return format or pagination metadata. For a list tool, this is adequate but incomplete for an agent to fully understand the output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description reinforces the meaning of table, chain, disabled, and pagination parameters, but adds limited additional value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists firewall rules from the filter or nat table on a MikroTik router, with filtering and pagination. This distinguishes it from siblings like list_mangle_rules and manage_firewall_rule.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for read-only listing of firewall rules, but does not explicitly mention when to use this tool versus alternatives. However, the context of sibling tools and the clear purpose makes it adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety and idempotency profile is fully covered elsewhere. The description only adds the pagination note, contributing little behavioral context beyond the structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with the core scoping ('which interface belongs to which list') front-loaded and filtering/pagination following. No wasted words, though it is slightly leaner than a fully structured definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, non-destructive list tool with 100% schema coverage and no output schema, the definition is adequately complete. The only omission is explicit routing versus sibling listing tools, which is minor given the clarifying parenthetical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so list, interface, limit, offset, and routerId are all documented in the schema. The description restates filtering by list/interface and pagination, adding no syntax or format detail beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (List) and resource (interface list memberships), and the parenthetical 'which interface belongs to which list, e.g. WAN/LAN' clarifies the semantic distinction from the sibling list_interface_lists. It stops short of explicitly naming that sibling, but the concept is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies a read/listing use case but gives no explicit when-to-use, when-not, or routing to alternatives like list_interface_lists or list_interfaces. Usage is inferable from the purpose but not guided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds no behavioral detail beyond confirming the list operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence of 8 words, perfectly concise and front-loaded with the core action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no description of return format; for a list tool, the agent would need to know what fields are returned (e.g., IDs, names). Missing this context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters; the description adds no extra semantic meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and the specific resource ('interface lists'), distinguishing it from sibling tools like 'list_interfaces' and 'manage_interface_list'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives; the read-only nature is implied by annotations but not clarified in text.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds value by mentioning pagination support and optional traffic counters, which are behavioral traits not covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no wasted words. The purpose is front-loaded, and every part adds value. Highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a list tool with comprehensive schema and annotations, the description is complete. It covers filtering, pagination, and counters. However, no output schema exists, so return value details are not explained. Still adequate given the context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description mentions filtering, pagination, and counters, which correspond to parameters, but adds no new meaning beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List'), the resource ('network interfaces on a MikroTik router'), and optional features (filtering, pagination, counters). It distinguishes from sibling list tools by specifying 'interfaces'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for listing interfaces but does not explicitly state when to use this tool vs alternatives like list_bridges or list_wifi_interfaces. No exclusion or alternative guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false), lowering the bar, and the description still adds real value: address entries include dynamic ones originating from DHCP client and PPP, which is a behavioral trait not visible in the schema. It does not mention auth/permission requirements or result-size characteristics, but the dynamic-inclusion note is genuinely informative.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with what is listed and followed by scoping and pagination details; every clause carries information. Minor room to be tighter, but nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with no output schema, the description covers resource scope, dynamic-address inclusion, available filters, and pagination. The main residual gap is what a returned record actually contains, which is not described, though the annotations and full schema coverage keep this from being a serious omission.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters (limit, offset, disabled, routerId, interface) are already documented in the schema. The description restates the interface and disabled filters and pagination at a high level without adding format, syntax, or default behavior beyond what the schema provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (List) and resource (IPv4 addresses assigned to interfaces on a MikroTik router), plus a distinguishing scope detail: dynamic addresses from DHCP client and PPP are included. That is clear and non-tautological, but it never names or contrasts with siblings like list_interfaces, list_dhcp_leases, or manage_ip_address, so an agent must infer the boundary itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description enumerates capabilities ('supports filtering by interface and disabled state, with pagination') but gives no when-to-use guidance, no prerequisites, and no indication of when to prefer this over list_interfaces or manage_ip_address. Filtering capabilities describe the tool, not when to select it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the description adds minimal behavioral context. It mentions filtering and pagination, which are consistent with a read operation, but does not elaborate on other traits like rate limits or performance.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, and contains no redundant information. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a list tool with comprehensive parameter schema and annotations highlighting safety, the description covers the key behaviors (filtering, pagination). The absence of an output schema reduces the need to explain return format. Minor omission: could mention default router behavior, but that's already in schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter (routerId, name, limit, offset) well-described. The description reiterates 'filtering by name and pagination' but adds no new meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List'), the resource ('IP address pools'), and the context ('on a MikroTik router'). It also mentions filtering and pagination, differentiating it from sibling tools like manage_ip_pool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for listing IP pools with optional filters and pagination, but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusion conditions. Given the large set of sibling list tools, more guidance would be helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds no additional behavioral context beyond the obvious 'list' operation. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that efficiently conveys the tool's purpose without any redundant words or unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only list tool with comprehensive annotations and full schema coverage, the description is complete enough. It covers what the tool does without needing to explain return values (no output schema).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with descriptions for all three parameters (routerId, address, limit). The description does not add extra meaning beyond the schema, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List IPSec peers on a MikroTik router', specifying the verb (List), resource (IPSec peers), and context (MikroTik router). It effectively distinguishes from sibling tools like manage_ipsec_peer and other list_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives (e.g., list_ipsec_policies, manage_ipsec_peer). There is no mention of prerequisites, context for filtering, or conditions for use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true, covering behavioral traits. The description adds no extra behavioral context beyond stating the resource type. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no redundant information. Efficient and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a list operation with complete schema and no output schema, the description is sufficient. It could mention that results are returned as a list, but not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% description coverage for all 4 parameters, each with clear descriptions. The tool description adds no additional meaning beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and resource 'IPSec policies' with scope 'on a MikroTik router'. It effectively conveys the tool's function, though it does not explicitly differentiate from sibling tools like list_ipsec_peers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives (e.g., manage_ipsec_policy for modifications). There is no mention of use cases or conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, destructiveHint, idempotentHint. The description adds that it returns port numbers and status, which is consistent with annotations. No additional behavioral traits disclosed beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose and the resources it covers, with no extraneous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list operation with no output schema, the description adequately specifies what is returned (port numbers and enabled/disabled status). All parameters are optional, implying full list by default. No missing critical context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters adequately. The description does not add significant meaning beyond the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and resource 'IP services' on a MikroTik router, and specifies the services and returned data (port numbers, enabled/disabled status). It distinguishes from sibling 'manage_ip_service' tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies a read operation, and sibling tools like 'manage_ip_service' provide context, but it does not explicitly state when to use this tool vs alternatives or mention any prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real context beyond them: the backing file, newest-first ordering, that parameters are shown as redacted at write time, and the rollbackable: true gate. That last point is critical behavioral knowledge an agent cannot infer from the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with identity and contents, then the usage routing, then the rollback caveat. Dense but no sentence is redundant — each carries information not present elsewhere.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by enumerating returned fields, ordering, and redaction behavior. Combined with the schema's filter documentation and the annotations' safety profile, an agent has everything needed to call this and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each of the three filters (tool, limit, routerId) is already documented in the schema, so the description need only reach baseline. It mentions 'router' and 'tool' as entry fields but adds no filtering syntax or interaction details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'List recent entries from the server's write journal (write-journal.ndjson)' — and enumerates the exact fields each entry carries (journalId, timestamp, tool, router, parameters, snapshot ids, outcome) plus ordering (newest first). This is unmistakably distinct from siblings like get_log or list_scripts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives two explicit use cases ('recover a lost journalId for rollback_change' and 'audit what was written when'), naming the downstream sibling tool that consumes the output. It also states the precondition for the follow-up action: only entries with rollbackable: true can be rolled back, and names the writes that never can be.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds the path and filter capability but does not disclose additional behavioral aspects such as pagination or error handling beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence (12 words) that conveys the essential purpose without unnecessary elaboration. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with no output schema, the description is adequate but lacks details on pagination, default limit behavior, or what the response contains. It is minimally complete given the context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for each parameter. The description briefly mentions 'type filter' but does not add meaningful meaning beyond what the schema already specifies for parameters like 'type' (enum) and 'limit' (default).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List', the resource 'RouterOS logging action targets', and specifies the API path 'system/logging/action'. It also mentions an optional type filter, distinguishing it from sibling tools like 'list_log_rules' and 'manage_log_action'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. While the read-only nature is implied by 'list', no guidance is given for choosing between this and other list or manage tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds minimal behavioral detail beyond the annotations, only confirming the listing action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose and key filtering capabilities without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description, alongside comprehensive annotations and schema, fully covers the tool's behavior for its simplicity. No output schema is provided, but typical list tool patterns apply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover all 4 parameters (100% coverage). The description adds that 'topics' uses substring matching and 'logAction' uses exact matching, providing extra clarity beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists RouterOS logging rules with specific filtering options (topic substring, action exact-match), distinguishing it from related list tools like list_log_actions and manage_log_rule.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for reading logging rules with optional filters, but does not explicitly mention when not to use it or suggest alternative tools for related tasks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and idempotent behavior. The description adds that rules are listed in evaluation order, which is a useful behavioral detail not covered by annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states core function and ordering, second lists filters. Extremely concise with no wasted words, front-loading the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with optional filters and no output schema, the description covers the key aspects: resource, order, and filter capabilities. It could mention what fields are returned, but it is mostly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all parameters. The description merely restates that filtering by chain, action, and disabled state is supported, adding no new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists firewall mangle rules on a MikroTik router in evaluation order. The verb 'List' and resource 'mangle rules' are specific and differentiate it from sibling list tools like list_firewall_rules.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for mangle rules with filtering, but it does not explicitly contrast with similar tools like list_firewall_rules or state when not to use it. No exclusion or alternative guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds no further behavioral context (e.g., no mention of required permissions, default return behavior, or pagination). It does not contradict annotations, but adds minimal value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that conveys the core functionality without any superfluous words. It is front-loaded and concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with an output schema absent, the description adequately covers the tool's purpose and scope. It could mention default behavior (e.g., returns all neighbors if no filter) but overall is sufficient given the annotations and schema richness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for all three parameters (routerId, interface, limit). The description does not add meaning beyond what the schema provides, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the action (list), the resource (discovered neighbors), and the specific protocols (CDP/LLDP/MNDP) on a MikroTik router. It clearly distinguishes from sibling tools like list_ospf_neighbors or list_bgp_peers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives (e.g., list_ospf_neighbors, list_bgp_peers). There are no exclusions, prerequisites, or contextual hints to help an agent decide.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnly, non-destructive, and idempotent behavior. The description adds minimal context about the resource type but does not elaborate on pagination, filtering details, or return structure. With annotations covering safety, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no unnecessary words. It is concise and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and 4 parameters. The description is minimal but combined with annotations and schema, it covers essential information. It could mention that it returns a list of entries, but overall it is adequate for a simple list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and each parameter is well-documented in the schema. The description adds no additional parameter meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists Netwatch monitoring entries on a MikroTik router, specifying the resource and action. However, it does not explicitly differentiate from sibling list tools, though the resource name is distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like manage_netwatch_entry for create/update/delete operations. There is no mention of prerequisites or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds that it returns specific fields and targets RouterOS 7+, but does not disclose any additional behavioral traits beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with the core purpose, and includes relevant return fields. No superfluous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with read-only semantics and no output schema, the description adequately covers the purpose, router version, and returned fields. Slightly more detail on filtering or scope could be added but not necessary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides descriptions for both parameters (routerId and state) with 100% coverage. The tool description does not add further meaning beyond what the schema offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it lists OSPF neighbors on a MikroTik router with RouterOS 7+, and specifies the return fields (state, interface, DR/BDR, uptime). Distinct from sibling tools like list_bgp_peers or list_neighbors.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving OSPF neighbor information but does not provide explicit guidance on when to use this tool over alternatives such as list_neighbors or other protocol-specific list tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (readOnlyHint: true, destructiveHint: false) already convey the non-destructive behavior. The description adds minor context about returned fields but does not discuss pagination or response format. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states purpose, second lists output. Clearly front-loaded and no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose and returned data. Annotations and schema handle safety and parameters. No output schema but the description compensates by listing key fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage with descriptions for all 3 parameters. The tool description does not add extra meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists OpenVPN client interfaces on a MikroTik router and specifies the output fields (name, remote server, connection status). It distinguishes itself from sibling tools like manage_ovpn_client and other list tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

While no explicit when-to-use or alternatives are provided, the context of list tools and the sibling manage_ovpn_client implies this is for read-only listing. The description does not guide against misuse, but the purpose is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.