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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that the response includes the retry round, which is useful context beyond annotations, but says nothing about polling behavior, error states, or failure modes for an unknown job_code.

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 short front-loaded sentence naming the resource and the key returned field. The inline example is slightly redundant with the schema example but not harmful.

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 an output schema present and a single fully documented parameter, the description only needs to state what the tool retrieves, which it does. The main omission is how this relates to sibling tools for diagnosing job state.

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 carries its own pattern and example, so the schema does the heavy lifting. The description merely repeats the same example, adding no new 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?

States a specific verb (get) and resource (job status) plus the fields returned (current status and retry round). It doesn't explicitly contrast with siblings like list_job_errors or retry_job, but the resource is unambiguous enough to select it.

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 indication of when to use this versus list_job_errors (which might also reveal job state) or retry_job. The job_code example implies polling a known job, but no when/when-not 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 readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: results are newest-first and sensitive values are redacted, which materially affects how an agent reads the output. Pagination/limit behavior is still undisclosed.

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 clipped sentences that front-load the resource and ordering. Slight redundancy between 'most recent' and 'newest first', and the terseness starts to cost clarity rather than save space.

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 an output schema present, return values needn't be explained, and redaction is mentioned. But for a diagnostic tool with an undocumented limit parameter and no routing guidance against get_job_status, the description is only minimally sufficient.

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 50%: job_code carries a pattern and example, but limit is completely undocumented in both schema and description. The description says nothing about how many errors are returned or what limit controls, so it fails to compensate for the coverage gap.

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 resource and scope: pipeline errors belonging to a job, with explicit ordering (newest first). The verb is implied by the name rather than the sentence, and no sibling is named, but none of the siblings (get_job_status, submit_job, retry_job) list errors, so confusion is unlikely.

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 when-to-use guidance and no mention of an alternative. An agent cannot tell from this text whether to reach for list_job_errors or get_job_status when diagnosing a failed job, nor whether it should be called after retry_job fails.

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 establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a genuinely useful scoping constraint — the path is resolved relative to a configured media root — but says nothing about failure behavior for missing files, unsupported containers, or whether probing is expensive on large media.

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 blocks: what is returned first, then the single argument. Every sentence earns its place; the only nit is the docstring-style 'Args:' formatting, which is slightly heavier than needed for one parameter.

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?

An output schema exists, so return-value explanation is unnecessary, and the one required parameter is fully described. For a single-param read tool with annotations, the only meaningful omission is error/edge-case behavior.

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%, so the description carries the full burden, and it does so well: it defines the path as relative to the configured media root and gives a concrete example ("sample_1080p.mp4") that pins down the expected format. It does not say whether absolute paths or traversal outside the root are rejected, which keeps it short of a 5.

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 the concrete resource (a media file) and enumerates exactly what it reports: codec, resolution, fps, duration, bitrate, audio. This is instantly distinguishable from the sibling tools, which are all job/runbook oriented, so there is no ambiguity about what this returns.

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?

Usage is implied by the field list — you call it when you need technical metadata for a file — but there is no explicit when-to-use or when-not-to-use statement. No sibling is similar enough to require routing guidance, so the gap is mild rather than damaging.

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?

Adds real context beyond the annotations: approval is client-side, not server-side, and each intended retry needs a fresh idempotency_key — consistent with idempotentHint=false and materially useful for an agent that might otherwise retry in a loop. Doesn't say what happens to prior run history or error records.

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 action is front-loaded in the first sentence and nothing is redundant. The parenthetical about Claude Desktop and approval nodes is slightly verbose relative to its value but still earns its place as behavioral 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?

An output schema exists, so return values need no explanation, and both required parameters are accounted for. For a two-parameter mutation tool, the description covers action, precondition, idempotency contract, and approval flow — enough to call 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?

Coverage is 50% (job_code documented in the schema; idempotency_key is not). The description partly compensates by explaining the key must be unique per intended retry, but gives no format or generation guidance, so it is only a marginal lift over 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 concrete verb and resource plus an explicit state transition: 'Move a failed job back to pending.' That distinguishes it from submit_job (new work) and get_job_status (read), though no sibling is named explicitly.

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?

Usage is implied by 'failed job' — the precondition is clear enough. But it never says what to do instead for non-failed jobs (submit_job) or how to inspect failures first (list_job_errors), so the routing decision is left 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 declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a safe, closed-corpus read. The description adds one genuinely useful behavioral instruction — cite results by their `source` id — which tells the agent how to attribute results. It says nothing about ranking, corpus scope, or what happens when no runbooks match, so it adds less than it could.

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 short sentences, front-loaded with the purpose and followed by the citation instruction — no filler. It is efficient but leans so terse that meaning is lost rather than compressed.

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?

An output schema exists, so return values need not be explained, but with 0% schema coverage the description should at minimum define `k` and say what the search operates over. For a 2-parameter tool with an undocumented parameter, this leaves a real gap before invocation.

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%, so the description carries the full burden and does not meet it: the `k` parameter (default 3) is never explained or even acknowledged, leaving the agent to guess whether it means result count or something else. Only `query` is self-evident from its name and required status.

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: 'Search operational runbooks.' That is clearly distinguishable from the job-oriented siblings (submit_job, get_job_status, list_job_errors), so an agent can select it without ambiguity. It stops short of saying what kind of search (semantic vs keyword) or what a runbook covers here.

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 explicit when-to-use or when-not-to-use guidance, but the sibling set is entirely job-management tools, so the choice is effectively implied by the purpose statement. Nothing names an alternative or a precondition for searching runbooks.

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 idempotentHint=true, but the description adds valuable scoping detail: idempotency is keyed on source_id and repeats never duplicate. It does not say what a duplicate call actually returns (existing job? new response?), which is the main residual gap; safety profile is otherwise 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 short sentences, zero waste, with the key behavioral constraint front-loaded right after the purpose statement.

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?

An output schema exists so return values needn't be explained, and annotations cover safety. However, for a 2-param mutation tool at 0% schema coverage, the description leaves the duplicate-call response and the 'title' parameter unexplained.

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 carry parameter meaning. It does explain source_id's role as the idempotency key, which is genuinely useful, but 'title' is never described and no format expectations are given for either.

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 ('Register a job'), which is distinguishable from siblings like get_job_status and retry_job. It doesn't explicitly contrast with any sibling, but the action 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?

No guidance on when to submit versus retry_job or check status first, and no preconditions stated. The only implied usage is 'call this to create a job', which is left to inference.

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