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

The description discloses that this is a write operation ('/api/respond write'), is non-retried, and performs local validation before the write. These details go beyond the all-false annotations, providing useful behavioral context, though it does not mention error handling 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 two concise sentences: the first states the action, the second adds key behavioral constraints. No unnecessary words or repetition of schema 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?

The description covers the core action, validation, and write behavior, but lacks details on return values, failure modes, or how to discover pending questions. Given the presence of 5 parameters and no output schema, a bit more context 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?

With 0% schema description coverage, the description must compensate. It references requestId, task lineage, question ids/order, and selections, which gives partial meaning to taskId, requestId, and answers. However, optional parameters sinceCursor and expectedRevision are left entirely unexplained.

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 answers a currently pending DSH question request, using a specific verb and resource. This differentiates it from sibling tools like dsh_resolve_approval or dsh_cancel, which handle different operations.

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 phrase 'currently pending typed DSH question request' implies the tool is used when a question is awaiting response, giving clear context. It does not explicitly mention alternatives or exclusions, but the tool's niche is obvious from the description 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?

Beyond the destructive and non-read-only annotations, the description reveals critical behavioral nuances: the non-atomic removal for queue scope, the reliance on a 'latest snapshot', and the preservation of queued work when canceling the active turn. These details significantly enhance the agent's understanding of side effects, fulfilling the transparency requirement.

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, each packed with essential information. It front-loads the scope-dependent behavior and avoids any fluff. Every word contributes directly to clarifying the tool's function, making it 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?

The description fully explains the core scoping semantics and provides strong transparency, but it lacks details on parameter usage (beyond scope) and expected outcomes or errors. With no output schema, the agent might need additional guidance on return values or failure cases. The description is adequate for the primary decision but incomplete for a four-parameter 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?

With 0% schema description coverage, the description must compensate for parameter semantics. It explains the `scope` enum (turn vs. queue) in context, but it completely omits `taskId`, `sinceCursor`, and `expectedRevision`. While `taskId` might be inferred from the name, the cursor and revision parameters remain unexplained, leaving gaps in parameter understanding.

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 (cancel/remove) and the resource (active root turn vs. queued items) with precise scoping. It distinguishes between two modes (`turn` and `queue`) and their distinct effects, making the tool's purpose unambiguous and differentiating it from any sibling tool.

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 explicit context for when to use each scope: `turn` cancels only the active turn, `queue` removes items from the queue. While it doesn't state alternatives or exclusions, the behavior is clearly tied to the two modes, giving the agent enough guidance to choose appropriately. It could be improved by mentioning when cancellation is not applicable, but it's generally 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?

With all annotations false, the description carries the burden and adds useful context: it clarifies that the tool performs a write, is scoped to the same root DSH session, and explains the behavior of queue and steer modes. It also notes that writes are never automatically retried, a non-obvious 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 three short sentences that front-load the purpose and follow with mode semantics and retry behavior. There is zero filler, making it 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?

No output schema and all false annotations require the description to cover behavior. It does cover core intent and mode semantics, but neglects parameter details, error conditions, and return values. As a compatibility alias, it is somewhat adequate but not fully self-contained.

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 0%, so the description must explain parameters. Only 'mode' gets semantics via queue/steer explanation; the other four parameters (prompt, taskId, sinceCursor, expectedRevision) are not addressed beyond vague 'same root' wording, leaving the agent under-informed about their meaning.

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 is a compatibility alias for dsh_followup and continues the same root DSH session. It distinguishes between queue and steer modes with specific targets, making the tool's purpose 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 usage as a drop-in replacement for dsh_followup but does not explicitly contrast with alternatives. It provides guidance on when to use queue vs steer, but lacks exclusions or conditions for choosing this tool over other sibling 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?

The description adds meaningful behavioral context beyond the annotations: it states the tool creates a session (mutation), uses DSH's configured model (so no model parameter), and is detached by default. The annotations only provide false hints, so this extra information is valuable, though it does not cover return behavior or session identification.

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 three concise sentences with no filler or repetition. It front-loads the core purpose and adds only high-signal details about model usage and detachment.

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 six parameters and no output schema, the description is incomplete. It does not explain what the tool returns (e.g., session ID), how to interact with the created session, or the meaning/effects of parameters like waitSeconds or workspaceMode. The lack of annotation guidance further burdens the description, which it does not fully carry.

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 only 17%, with only 'cwd' described in the schema. The description does not explain any of the six parameters (prompt, title, agentPreset, waitSeconds, workspaceMode). The note about 'no model argument accepted' is a constraint, not a parameter explanation, and 'cwd' is already covered by 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 a specific action: 'Create a root session on the configured official DSH Web Host and queue the initial prompt.' It also differentiates from siblings by noting 'no model argument is accepted' and 'Detached by default,' which sets it apart from follow-up or observation 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 clearly conveys when to use it: for creating a root session and queuing the initial prompt. It implicitly indicates it is the entry point for a session, distinguishing from siblings like dsh_followup or dsh_continue, but it does not explicitly state exclusions or 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?

The annotation already indicates it is not read-only (readOnlyHint=false), and the description adds meaningful behavioral details: the write is never automatically retried, and the queue/steer modes define how the followup is targeted. This goes beyond the annotation by clarifying retry behavior and mode semantics.

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 with no filler. It front-loads the core purpose, then adds mode distinction and retry behavior. Every sentence contributes 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?

The description covers the main behavior, mode semantics, and retry policy, but with no output schema and multiple siblings, it doesn't explain the intended response, prerequisites (e.g., session must exist), or interactions with dsh_status/wait. It is adequate but leaves 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 description coverage is 0%, and the description only clarifies the 'mode' parameter (queue vs steer) and indirectly the 'prompt' (as the written content). It leaves 'taskId', 'sinceCursor', and 'expectedRevision' completely unexplained, which is insufficient given five parameters and no schema help.

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 identifies the tool's function ('Continue the same root DSH session') and distinguishes its two operational modes (queue vs steer). However, it doesn't explicitly differentiate this tool from the sibling 'dsh_continue', which may cause ambiguity.

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 context ('continue the same root DSH session') and provides within-tool guidance on when to use queue vs steer, but it lacks explicit guidance on when to use this tool instead of siblings like dsh_continue or dsh_delegate.

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, which aligns with the 'Report' verb. The description adds minimal behavioral context by specifying the exact subject of the report, but does not disclose any additional traits such as availability, latency, or what 'connect-only bridge state' entails beyond the surface meaning.

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 front-loads the action ('Report') and clearly identifies the object. No filler words or redundant information are present, making it 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?

Given the tool's simplicity (zero parameters, rich annotations, no output schema), the description is sufficient to convey what the tool does. It names the specific status areas ('connect-only bridge state' and 'current official capabilities') which helps set context, though it does not elaborate on why this information matters or how it might be used.

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 tool has zero parameters, and the input schema is empty with 100% schema coverage. Per the rubric, 0 params earns a baseline of 4. The description does not need to explain parameter semantics because there are none.

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 the specific verb 'Report' and clearly identifies the resource being reported: 'connect-only bridge state' and 'current official DSH Web Host capabilities.' This distinguishes it from sibling tools like dsh_status, which likely reports general status, and dsh_list, which lists items.

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 guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or scenarios where another sibling tool would be preferable. Usage context is only implied by the tool name and description.

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 read-only, idempotent, and non-destructive. The description adds meaningful behavioral context by specifying that the list is enriched with DSH status only when the Host is reachable, implying conditional output. However, it doesn't explain fallback behavior when the host is unreachable or the output format.

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 filler. Every word adds value: action, resource, enrichment, condition.

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 no parameters and no output schema, the description gives the essential information: what is listed and the condition for enrichment. It could clarify behavior when Host is unreachable, but the overall context is sufficient for a simple 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?

The input schema has zero parameters, and schema coverage is 100%. The description accordingly has no need to explain parameters; the baseline of 4 applies due to zero-parameter 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's action ('List') and resource ('bridge task mappings'), with a specific qualifier about enrichment. This differentiates it from sibling tools like dsh_status which likely focus on status of a single task rather than listing mappings.

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 when the user needs a list of bridge task mappings, but it does not provide explicit when/when-not guidance or mention alternatives among sibling tools. It lacks context on when to prefer this over dsh_status or dsh_host_status.

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 read-only, idempotent, and non-destructive. The description adds minimal context by labeling it a 'compatibility observation alias', hinting it is a legacy wrapper, but does not disclose specific behavioral details like return format or side effects. This is slight added value, hence a middle score.

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 brief and efficiently structured: a short definition followed by a usage recommendation. Both sentences serve a purpose, though the first sentence is somewhat empty. Overall, it is appropriately sized and front-loaded, earning a high score.

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 only sparse annotations. The description fails to explain what 'observe' does, how it behaves, or what the parameters mean. It is incomplete for an agent to reliably invoke it, though the guidance to prefer alternatives is useful.

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 0%, and the description provides no information about the three parameters (taskId, afterCursor, waitSeconds). The description fails to compensate for the lack of schema documentation, leaving parameter semantics completely unexplained.

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 'Compatibility observation alias' is vague and does not specify a concrete action or resource. It restates 'observe' in noun form and adds 'compatibility alias', but fails to explain what the tool actually does, making it difficult to distinguish from siblings based on purpose alone.

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 explicitly states 'Prefer dsh_wait plus dsh_tail task cursors', providing clear guidance on when NOT to use this tool and naming specific alternatives. This fully addresses usage differentiation and satisfies the when/when-not requirement.

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 destructive=true, and the description adds valuable context by clarifying that releasing the claim does not close the DSH session or stop Web/Codex from editing. This helps prevent misuse. It could add more about consequence (e.g., whether the claim can be reacquired), but the added exclusions are meaningful 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?

The description is two sentences and immediately front-loads the primary action and resource. Each sentence adds value: the first states the purpose, the second clarifies non-effects. No filler or repetition.

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 low-complexity tool with one obvious parameter and no output schema, the description covers the core purpose and key exclusions. It does not describe return values or post-conditions, but given the simplicity and the sibling context, it is sufficiently complete. Slightly more detail about what happens after release would push it higher.

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?

There is one required parameter, taskId, with 0% schema description coverage. The description never mentions taskId nor explains that it identifies the bridge task whose workspace claim is released. While the name and pattern are somewhat self-evident, the description fails to compensate for the lack of schema descriptions, leaving the agent to infer the parameter's role.

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 action ('Explicitly release') on a specific resource ('this bridge task's persistent workspace claim'). It also clearly distinguishes itself from related actions by noting it does not close the session or stop editing, which separates it from siblings like dsh_cancel and dsh_continue.

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 the tool: when you need to release a workspace claim. It also clarifies what it does not do, providing useful boundaries. However, it does not explicitly reference alternative tools or state 'use this instead of X', so it lacks the explicit when-not/alternatives guidance of a perfect score.

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?

Beyond the annotations (destructiveHint=true), the description adds significant behavioral detail: 'Never auto-allows' and the need for approval_mode=prompt configuration. This clarifies safety-critical behavior not captured by 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?

Two sentences, front-loaded with the core purpose. The second sentence is a necessary safety warning. No filler words or redundant 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 tool with 5 parameters and no output schema, the description covers the basic purpose and safety constraint but omits details about side effects, consequences of each outcome, and prerequisites beyond 'pending.' It is minimally adequate but leaves 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?

With 0% schema description coverage, the description must explain parameters. It only mentions 'allow_once' and 'reject' which map to the outcome enum, but leaves taskId, requestId, sinceCursor, and expectedRevision unexplained. This is insufficient compensation for the lack of 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: 'Resolve one pending DSH sandbox-escalation approval as allow_once or reject.' This specifies the verb (resolve), the resource (approval), and the possible outcomes, distinguishing it from sibling 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?

It provides a critical usage prerequisite: 'configure this Codex MCP tool with approval_mode=prompt before permitting allow_once.' It also implies the tool is for pending approvals, giving clear context. However, it does not explicitly name alternative tools or exclusion 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=true and idempotentHint=true, so the description does not need to re-state safety. It adds value by enumerating the detailed return contents, but it discloses no additional behavioral traits like permission requirements, performance implications, or error handling. This is acceptable given the strong 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.

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

The description is a single sentence that front-loads the verb and lists key status aspects. While it is a long list, it is still concise and efficiently communicates the tool's output breadth without 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 returns many distinct elements, and without an output schema the description carries the burden of explaining return values. It lists them explicitly but lacks details on their structure, meaning, or edge cases. It also provides no usage context, making the description adequate but not fully complete for a complex status 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?

The schema has one required parameter taskId with zero description coverage, and the tool description does not mention it or explain its format or purpose. The description fails to compensate for the schema's lack of parameter documentation, leaving the agent to infer taskId solely from the name and pattern.

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 returns a comprehensive status object, listing specific components like availability/execution state, sessions, queue depths, and bridge cursor/watermarks. This distinguishes it from siblings like dsh_host_status, though it does not explicitly mention the task context, which is implied by the taskId parameter.

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?

There is no guidance on when to use this tool versus alternatives such as dsh_tail or dsh_host_status. The description only lists output fields without indicating preferred scenarios or exclusions, so an agent must infer usage from the tool 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 declare readOnlyHint=true and destructiveHint=false, but the description adds valuable behavioral context: content is fetched live from DSH history and never persisted into bridge storage. The 'when reachable' caveat also informs the agent about potential availability issues, which is 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 two concise sentences, front-loaded with the primary action and scoped. Every clause adds meaningful information about data source, boundedness, or persistence without redundancy. It is appropriately structured for quick reading.

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 and 0% parameter coverage, the description should include return value expectations, pagination behavior, or error handling. It covers only general purpose and data flow, leaving the agent without enough detail to interpret results or configure the tool correctly for taskId and cursor parameters.

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 0%, with no parameter descriptions in the schema or the tool description. The description does not explain taskId, maxBytes, maxEvents, or sinceCursor, despite mentioning 'cursors' generically. This is a significant gap for correct invocation with four parameters.

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 identifies the action ('Read') and the resource ('bounded event digests') and specifies that it uses bridge coordination cursors. It distinguishes from siblings like dsh_observe by indicating historical access, though the jargon 'bridge coordination cursors' and 'DSH history' may not be immediately meaningful to all agents.

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 usage guidance is provided about when to choose this tool over alternatives like dsh_observe or dsh_status. The phrase 'when reachable' hints at a prerequisite but does not specify fallback tools or typical scenarios. The description lacks any 'use when...' or 'not for...' guidance.

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, idempotent, and non-destructive behavior. The description adds behavioral details beyond annotations: it blocks up to 30 seconds, waits for specific event types, and does not wait for whole-task completion. This is meaningful context that the annotations do not 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?

The description is two sentences, front-loaded with the primary action and constraints, and contains no unnecessary words. It is appropriately sized 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?

The description covers the core behavior and timeout limit but omits parameter explanations and return-value behavior. Since there is no output schema, a sentence about what the tool returns on timeout or success would improve completeness. Still, the fundamental use case is understandable.

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 three parameters with no descriptions (0% schema coverage). The description does not explain taskId, timeoutSec, or sinceCursor; the only hint is 'at most 30 seconds,' which vaguely maps to timeoutSec. Given the low coverage, the description must compensate but does not, severely limiting parameter-level understanding.

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 waits for specific task-related events (new cursor, status/availability change, terminal state, pending interaction) and explicitly excludes whole-task completion. This differentiates it from sibling tools that might handle completion or status, giving it a specific verb and resource 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?

The description provides clear context for when to use the tool (waiting for task updates) and when not (never waits for whole-task completion). However, it does not explicitly name alternative sibling tools for the excluded case, so it lacks explicit alternatives.

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