Server Quality Checklist

Tool Scores

• iptime_cancel_changeB
  3.2/5.0
  Behavior2/5

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

  Annotations provide the basic safety profile (non-read-only, non-idempotent, non-destructive), but the description adds no behavioral context. It does not explain what cancellation does to the plan, whether it is reversible, whether authentication is required, or what side effects may occur. The word 'cancel' is the sole behavioral clue.

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

  Conciseness5/5

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

  The description is a single, complete sentence with no filler. It front-loads the verb and resource, and every word earns its place.

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

  Completeness3/5

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

  For a one-parameter cancellation tool, the description is minimally viable: it names the action and the pending precondition, and the annotations cover the safety profile. However, it says nothing about the return value, error conditions, or whether the plan must belong to the current session, leaving minor but real gaps.

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

  Parameters2/5

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

  Schema description coverage is 0%, and the description does not mention plan_id at all. While the parameter name is self-explanatory and the action implies it identifies the plan to cancel, the description does not explicitly state its role, leaving the agent to infer the connection.

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

  Purpose5/5

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

  The description uses a specific verb ('Cancel') and a specific resource ('pending change plan'), making the tool's function immediately clear. It also distinguishes itself from sibling tools like iptime_plan_change and iptime_apply_change by targeting a different stage in the change lifecycle.

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

  Usage Guidelines2/5

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

  The description offers no guidance on when to use this tool versus alternatives. It does not reference siblings, prerequisites, or conditions such as 'use only if the plan has not been applied yet.' The only hint is the word 'pending,' which is too implicit to count as clear usage guidance.

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

• iptime_list_plansB
  3.2/5.0
  Behavior3/5

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

  Annotations already establish read-only, idempotent, non-destructive behavior, so the description does not need to restate those. The phrase 'current state' adds a small behavioral hint about output content, but it does not explain open-world behavior, output richness, or any other runtime characteristics.

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

  Conciseness4/5

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

  The description is one short sentence with no filler and front-loads the action and object. It is concise, though slightly underspecified enough that it does not reach a top score.

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

  Completeness3/5

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

  The tool is low-complexity with one optional, well-documented parameter and annotations that cover safety. However, there is no output schema and the description does not clarify what a 'plan' is, what fields are returned, or how the optional router_id affects the result, leaving some practical gaps.

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

  Parameters3/5

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

  The single optional parameter is fully described in the schema ('Configured router id; optional when exactly one router exists'). The description itself does not mention router_id, but with 100% schema description coverage, the schema carries the parameter semantics adequately.

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

  Purpose4/5

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

  The description uses a specific verb ('List') and a clear resource ('plans'), and adds 'current state' to convey the kind of output. It is reasonably distinct from sibling tools like iptime_status and iptime_list_operations, though it could more explicitly differentiate itself from them.

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

  Usage Guidelines2/5

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

  The description gives no guidance on when to use this tool versus siblings such as iptime_list_operations or iptime_status. It also omits any conditions, prerequisites, or context about when plan listing is relevant.

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

• iptime_plan_config_restoreB
  3.2/5.0
  Behavior3/5

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

  The description adds context beyond the annotations by noting the operation hashes a local backup and creates a critical-risk plan. It does not contradict the annotations: creating a plan is consistent with readOnlyHint=false and destructiveHint=false, but side effects such as plan persistence or execution prerequisites are not disclosed.

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

  Conciseness4/5

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

  The description is a single front-loaded sentence with no filler. It would only score a 5 if it had stronger structural separation, but it is efficient and to the point.

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

  Completeness3/5

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

  The description covers the input source and the outcome (restore plan), which is enough to select the tool among siblings. However, without an output schema it omits the return value, and it does not explain the relationship to iptime_apply_change or what happens after the plan is created.

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

  Parameters3/5

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

  The description gives some semantic context for file_path by identifying it as a local ipTIME configuration backup, but it does not explain its format or location requirements. router_id is already documented in the schema as optional when one router exists; the description adds nothing else to compensate for the missing file_path schema description.

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

  Purpose4/5

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

  The description names a specific process: hashing a local ipTIME configuration backup and producing a restore plan. It clearly conveys the tool is about config restoration rather than backup or apply, but it does not explicitly differentiate from sibling plan tools like iptime_plan_change or iptime_plan_firmware_upgrade.

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

  Usage Guidelines2/5

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

  There is no guidance on when to use this tool versus its siblings. The phrase 'local ipTIME configuration backup' only implies an input context; it does not state prerequisites, exclusions, or alternatives such as iptime_apply_change or iptime_backup_config.

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

• iptime_backup_configB
  3.3/5.0
  Behavior3/5

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

  Annotations already declare non-read-only, non-idempotent, non-destructive behavior. The description adds the useful guarantee that existing files are never overwritten, which aligns with destructiveHint=false. However, it leaves unclear what actually happens if output_path already exists (error vs. unique-name generation) and does not mention authentication or connectivity requirements.

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

  Conciseness5/5

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

  Two sentences with no wasted words. The primary action is front-loaded and the critical safety constraint follows immediately. Every sentence earns its place, and there is no redundancy with the structured schema.

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

  Completeness3/5

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

  The description covers core action and a key constraint, and the schema/annotations handle parameters and safety profile. But with no output schema, the return value is unspecified, and the 'never overwritten' rule creates ambiguity about collision handling. For a side-effecting download/backup tool, this is a meaningful gap.

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

  Parameters3/5

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

  Schema description coverage is 100%: output_path and router_id are both described with sufficient meaning. The tool description only re-emphasizes that the file should be a new .config file, adding no additional parameter-level detail beyond what the schema already provides, so the baseline score of 3 applies.

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

  Purpose4/5

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

  The description uses a specific verb ('Download') and identifies both the resource ('current router configuration') and the destination ('a new local .config file'). It does not explicitly contrast with sibling tools like iptime_plan_config_restore or iptime_read, but the action is unambiguous and distinct enough that an agent can infer what it does.

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

  Usage Guidelines2/5

  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 such as iptime_read or iptime_plan_config_restore. The 'never overwritten' statement is a safety behavior, not a selection criterion, so an agent gets no help deciding between backup, read, and restore operations.

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

• iptime_list_operationsA
  3.5/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint and idempotentHint, and the description adds that the tool 'does not contact the router' and that the catalog is 'fixed' and 'auditable,' giving useful context about side-effect-free, stable behavior. 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.

  Conciseness5/5

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

  Two short sentences with no filler. The first sentence states the core action and object, the second adds a key behavioral clarification, both earning their place.

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

  Completeness2/5

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

  For a simple listing tool, the core operation is clear, but the two input parameters are completely unexplained and there is no output schema. This is a significant completeness gap for an agent trying to invoke the tool correctly with meaningful arguments.

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

  Parameters1/5

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

  Schema description coverage is 0%, and the description provides no explanation of the 'mode' or 'domain' parameters. An agent cannot determine how to set these optional filters from the tool definition alone, so the description fails to compensate for the schema's lack of parameter documentation.

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

  Purpose4/5

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

  States a specific verb and resource: 'List the fixed, auditable operation catalog.' The phrase 'does not contact the router' clarifies that this is a local metadata operation, distinguishing it from router-contact siblings, though it does not name an alternative explicitly.

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

  Usage Guidelines4/5

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

  The description clearly indicates the tool is for retrieving the fixed operation catalog without touching the router, so an agent can infer it is appropriate when offline/static operation metadata is needed. It does not explicitly state when not to use it or name alternatives, leaving some inference to the agent.

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

• iptime_logoutA
  3.5/5.0
  Behavior3/5

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

  Annotations already signal that this is not read-only, not idempotent, and not destructive. The description adds some useful context by specifying that the operation terminates the router admin session, but it stops short of explaining consequences like requiring a re-login or invalidating credentials. 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.

  Conciseness5/5

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

  A single sentence with no filler and a clear subject-verb-object structure. It is front-loaded and appropriately sized for a one-parameter logout operation.

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

  Completeness3/5

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

  The tool is simple, the one optional parameter is fully documented in the schema, and no output schema exists to explain. Still, the description lacks explicit usage routing and behavioral side-effect context, so it is minimally complete rather than fully self-sufficient.

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

  Parameters3/5

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

  The schema fully describes the only parameter, router_id, including its optionality when exactly one router exists, so the description does not need to repeat it. The description itself says nothing about parameters, leaving semantics entirely to the schema.

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

  Purpose5/5

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

  The description names a concrete action ('End') and a clear resource ('the router admin session'), directly stating what the tool does. It also reads as the counterpart to sibling iptime_login, so an agent can distinguish it from status, read, and plan tools 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.

  Usage Guidelines2/5

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

  There is no guidance about when to call this tool or when to prefer a sibling; it does not mention that it should follow admin operations or that it will invalidate the authenticated session. The only cue is the tool name and sibling context, which is not explicit enough.

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

• iptime_statusA
  3.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond the annotations: the tool may detect the router interface and may perform authentication when configured. No contradiction with the annotations exists.

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

  Conciseness5/5

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

  The description is a single compact sentence that front-loads the primary action and packs multiple steps without waste. Every clause earns its place, and there is no redundant restatement of the tool name or annotation hints.

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

  Completeness3/5

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

  The tool is simple (one optional parameter, rich annotations), but the absence of an output schema means the description should clarify what 'product/system status' includes and how authentication is triggered. The phrase 'authenticate if configured' is ambiguous about whether the agent should call iptime_login first. With many siblings, this ambiguity is a real gap, though the core invocation is otherwise covered.

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

  Parameters3/5

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

  Schema description coverage is 100%: the single optional router_id parameter is fully described in the schema. The description adds no additional parameter-level meaning. This matches the baseline of 3 for high schema coverage.

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

  Purpose4/5

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

  The description clearly states a specific verb ('read') and resource ('product/system status'), plus distinct preprocessing steps ('detect the router interface, authenticate if configured'). It is not a tautology and gives an agent a usable idea of what the tool accomplishes. It does not explicitly differentiate from the sibling iptime_read, so it misses the top score.

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

  Usage Guidelines2/5

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

  The description implies an operational sequence (detect, authenticate, read) but gives no explicit guidance on when to choose this tool over siblings like iptime_read or iptime_login. It does not mention prerequisites, alternatives, or exclusions. The agent is left to infer the intended use case.

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

• iptime_capabilitiesA
  3.8/5.0
  Behavior4/5

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

  Annotations already declare it read-only, idempotent, non-destructive, and open-world. The description adds useful behavioral context beyond those annotations by emphasizing that the exposed operation set depends on the actual model and firmware and may differ from the static catalogue.

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

  Conciseness5/5

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

  A single front-loaded sentence communicates the core purpose efficiently. There is no filler, and every word contributes to the tool's meaning.

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

  Completeness4/5

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

  For a simple read-only introspection tool with all optional parameters and no output schema, the description conveys the essential return concept: which operations are actually exposed. It is not fully complete because the refresh behavior is unclear, but the annotations and parameter schema cover most of the remaining invocation context.

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

  Parameters3/5

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

  The schema already documents domain and router_id with descriptions, so the description does not need to repeat them. However, the refresh parameter has no schema description and the tool description adds nothing about its meaning, leaving a moderate semantic gap.

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

  Purpose5/5

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

  The description clearly states a specific action ('Discover') and a specific resource ('which catalogued operations this model and firmware actually expose'). It establishes the tool's purpose as capability introspection and distinguishes it from simply listing the catalogued operation set.

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

  Usage Guidelines2/5

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

  The description implies the tool is used to check what operations are actually available, but it gives no explicit when-to-use guidance and names no alternatives. The contrasting sibling iptime_list_operations is especially relevant, yet the description does not explain when one should be chosen over the other.

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

• iptime_loginA
  3.9/5.0
  Behavior4/5

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

  Annotations already signal a state-changing operation (readOnlyHint=false, openWorldHint=true, idempotentHint=false). The description adds a valuable behavioral constraint beyond annotations: credentials are never accepted as tool arguments, telling the agent not to attempt to pass username/password. It does not disclose failure behavior or session details, but the bar is lower given annotation coverage.

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

  Conciseness5/5

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

  Two short sentences with no filler. The primary action is front-loaded, and the critical constraint about credentials is stated immediately after. Every sentence earns its place.

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

  Completeness3/5

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

  For a login tool with no output schema, the description is minimally sufficient: it states the authentication source and the schema covers the two optional parameters. However, it omits what a successful login returns, whether a session is established, and how failures or pre-existing sessions are handled. Given the openWorldHint and mutation nature, this is a clear gap.

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

  Parameters4/5

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

  The schema already provides strong descriptions for both parameters, including when captcha_code is needed and when router_id is optional. The description adds extra semantic value by explicitly clarifying that no credential parameters exist, which directly informs how the agent should reason about the input schema and why required auth fields are absent.

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

  Purpose5/5

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

  The description uses a specific verb ('Authenticate') and a clear resource (the router, implied by the iptime naming and sibling set). It also draws a meaningful distinction from typical authentication tools by stating that credentials come from the MCP environment and are never accepted as arguments, which clearly separates it from any hypothetical credential-input tool.

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

  Usage Guidelines2/5

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

  The description does not state when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. It does not say 'use before other operations' or contrast with logout. The only usage hints live in the schema parameter descriptions (captcha only after requested, router_id optional when exactly one router exists), not in the description itself.

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

• iptime_plan_firmware_upgradeA
  3.9/5.0
  Behavior4/5

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

  Annotations only indicate non-read-only, non-idempotent, non-destructive behavior. The description adds meaningful behavioral detail beyond that: it hashes a local file, creates a critical-risk plan, and does not upload. This clarifies what side effects are deferred.

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

  Conciseness5/5

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

  Two short sentences with no redundant phrasing. The key scoping statement, 'No upload occurs yet,' is front-loaded and immediately orients the agent.

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

  Completeness3/5

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

  With no output schema, the description does not mention what the created plan returns or how to verify it. It also does not mention whether an existing pending plan is replaced or how the plan should be applied later. Adequate but has clear gaps for a state-creating operation.

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

  Parameters3/5

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

  Schema coverage is 50%, with router_id already described in the schema. The description helps by calling file_path a 'local firmware file,' but it omits any detail about the hashing format, accepted file types, or how router_id relates to the plan. It partially compensates for the undocumented parameter.

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

  Purpose5/5

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

  The description uses specific verbs and objects: 'Hash a local firmware file and create a critical-risk upgrade plan.' It is not a tautology and clearly distinguishes itself from apply/upload operations by adding 'No upload occurs yet.'

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

  Usage Guidelines3/5

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

  The description implies this is a planning-stage tool meant to precede an actual firmware upgrade, and the 'No upload occurs yet' clause hints that iptime_apply_change should be used later. However, it never explicitly names alternatives or states when not to use this tool.

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

• iptime_readA
  4/5.0
  Behavior3/5

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

  The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description merely reinforces the read-only nature. It adds the useful fact that the operation originates from iptime_list_operations, but it does not provide additional behavioral context such as authentication requirements, error behavior, or what happens when parameters are invalid. There is 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.

  Conciseness5/5

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

  A single sentence that is front-loaded with the core behavior, uses no filler, and earns its place. It is concise without being a tautology.

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

  Completeness4/5

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

  For a generic read-only dispatcher, the description plus the schema and annotations provide most of what an agent needs: discover operations via list_operations, pass operation and optional params, and rely on the router_id rule from the schema. It could be more complete with an example or a note about return values, but the absence of an output schema lowers the burden.

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

  Parameters3/5

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

  The schema already documents params and router_id clearly, leaving operation as the main undocumented required parameter. The description compensates partially by indicating the operation value should come from iptime_list_operations, but it does not clarify how params should be shaped for different operations or give any examples.

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

  Purpose5/5

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

  The description clearly states a specific verb ('Run') and resource ('a read-only operation from iptime_list_operations'), which precisely identifies what the tool does. The read-only qualifier also helps distinguish it from the mutation and planning sibling tools without needing to inspect each one.

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

  Usage Guidelines4/5

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

  The description gives clear context: this tool executes read-only operations that come from iptime_list_operations. It implicitly tells the agent to use list_operations to discover the operation value first, though it does not explicitly spell out exclusions such as 'for writes, use apply_change'.

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

• iptime_apply_changeA
  4.1/5.0
  Behavior4/5

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

  It adds meaningful behavioral guardrails beyond the annotations: 'exactly one' plan is applied, and the confirmation text must be repeated verbatim. This is important for a destructive, non-idempotent operation, though it does not describe post-apply effects.

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

  Conciseness5/5

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

  A single sentence with no filler. It front-loads the action, resource, and constraint, making it quick for an agent to parse and act on.

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

  Completeness3/5

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

  The essential contract is stated, but for a destructive, open-world operation with no output schema, it omits what happens on success or failure and any prerequisite context such as how plans are created or confirmed.

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate. It succeeds in explaining that 'confirmation' is the verbatim text to repeat and implies 'plan_id' identifies the pending plan. It does not fully explain how to obtain the confirmation text, but the core semantics are present.

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

  Purpose5/5

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

  The description states a specific verb ('Apply') and resource ('pending plan'), and clarifies the exact condition: it applies only one plan after verbatim confirmation. This distinguishes it from sibling tools like iptime_plan_change, iptime_cancel_change, and iptime_list_plans.

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

  Usage Guidelines3/5

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

  The description implies when to use the tool—when a pending plan exists and its confirmation text is available—but it does not explicitly mention alternatives or conditions where the tool should not be used.

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

• iptime_plan_changeA
  4.2/5.0
  Behavior4/5

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

  Beyond the annotations, the description adds important behavioral facts: the plan is expiring, immutable, and causes no immediate setting change. This is valuable because readOnlyHint is false and destructiveHint is false, so the agent needs to know the write is to the plan store rather than the router. It does not mention expiration duration or how the plan is later applied, but the most safety-relevant behavior is disclosed.

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

  Conciseness5/5

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

  Two short sentences with the primary action front-loaded and no filler. The clarifying statement about not changing settings earns its place.

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

  Completeness4/5

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

  The core workflow premise, safety profile, and dependencies are sufficiently covered by the description and schema, and the sibling set makes the follow-on apply/cancel/list workflow discoverable. There is no output schema and the description does not state what the created plan returns, which is a minor gap for an agent that may want to track the plan.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the baseline of 3 applies. The description itself adds no new parameter semantics, but the schema already documents that operation comes from iptime_list_operations, params is arbitrary JSON, and router_id is optional.

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

  Purpose5/5

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

  The description names a specific verb ('Create') and a specific resource ('expiring immutable plan for a router change'). The follow-up 'No setting is changed by this tool' differentiates it from apply/change operations and makes the tool's role clear among its siblings.

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

  Usage Guidelines4/5

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

  It clearly establishes when to use this tool: to create a plan rather than make an actual router change. However, it does not explicitly name alternatives such as iptime_apply_change or the specialized plan_firmware_upgrade/plan_config_restore tools, nor state when those should be preferred.

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