MusicCheck: copyright screening

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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description carries the return-value burden and does so well: it discloses that results are conditional on status and enumerates windows, timestamps, matched title/artist, and a publish-safety verdict. It stops short of describing the non-COMPLETED states or error behavior.

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

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

Two sentences, zero filler, front-loaded with the action and scope before the return-shape detail. Every clause earns its place and nothing is repeated from structured fields.

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 one-parameter, no-output-schema tool the description covers the payload an agent would otherwise lack (fields, conditionality, verdict). It is only slightly incomplete in not sketching what a non-COMPLETED or failed response looks like.

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

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

Schema description coverage is 100% and the single uuid parameter is already documented there, including the 'report_id without MC- prefix' note. The description adds no syntax, format, or lookup semantics beyond the schema, so the baseline 3 applies.

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

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

States a specific verb (Fetch) and resource (the status and result of one screening), with the scope word 'one' distinguishing it from the sibling list_screenings and from screen_audio which creates screenings. An agent knows immediately this is a single-item retrieval keyed by uuid.

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 never says when to reach for this tool versus list_screenings, screen_audio, or verify_report, and states no prerequisites (e.g., that a screening must already exist or how a uuid is obtained). The 'When status is COMPLETED' clause is behavioral, not usage routing.

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, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuinely new behavioral context the annotations cannot express: an authorization gate and the resulting error for non-API-key callers. It stops short of covering pagination or result shape, so a 4 rather than 5.

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

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

Two sentences, zero filler. The capability statement comes first and the access restriction second, which is the right order since the restriction is a gating condition rather than the primary purpose.

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

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

No output schema exists, but the description signals what comes back ("with their results") and fully covers the unusual access model, which is the main risk for this tool. Only minor gaps remain, such as ordering or pagination behavior, so it is nearly complete.

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

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

Schema description coverage is 100% for the single limit parameter (max 50, default 10), so the schema carries the full burden. The description adds no meaning beyond it, which matches the baseline 3 for a fully documented parameter set.

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

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

States a specific verb and resource ("List recent screenings") plus what is returned ("with their results"). The clause about looking screenings up by report id implicitly distinguishes it from get_screening, so an agent can route without opening sibling schemas.

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

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

Explicitly states the access condition ("only available to the MusicCheck service API key"), the failure mode for other callers ("accounts signed in through Claude receive an error"), and the alternative path ("look up screenings by report id"). This is a full when-to-use / when-not-to-use / alternative triad.

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 behavior beyond the annotations: the call returns immediately with a report_id and QUEUED status (async job semantics) and is a paid call requiring a WIA MCP Pro plan or credits. Cost and async-return disclosure are exactly the kind of context annotations (readOnlyHint=false, openWorldHint=true) cannot convey.

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

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

Three tight sentences, front-loaded with the action, followed by the return contract and the cost/auth prerequisite. Every sentence carries distinct information with no filler.

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

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

For an async submission tool with no output schema, the description supplies everything an agent needs: what to submit, what comes back immediately, where the real result lives, and that the call costs money on a specific plan.

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

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

Schema description coverage is 100%, so both url and filename are already documented in the schema. The description only reinforces that the URL must be publicly reachable and says nothing about filename, so baseline 3 is appropriate.

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

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

States a specific verb and resource — submit a publicly reachable audio/video URL for copyright screening — and implicitly differentiates itself from siblings by naming get_screening as the retrieval path. An agent can tell this is the submission/start tool, not a retrieval or verification 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?

Clearly frames the context: this starts a screening job, and the finished result comes from get_screening. It does not explicitly state when not to use it (e.g. versus verify_report or re-submitting an already-screened URL), so it stops short of full when/when-not 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 declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description's one added behavioral fact is that no sign-in is required, which is genuinely useful auth context, but it says nothing about failure behavior for an invalid/unknown id, rate limits, or what the verification verdict looks like.

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: the first front-loads the core action, the second gives the motivating scenario. No filler, no repetition of the title, and the size matches the tool's simplicity.

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

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

With no output schema, the description partially compensates by saying you can 'see what it concluded', hinting at a verdict/result payload. It is nearly complete for a one-parameter read tool, though it leaves the exact return shape and unknown-id behavior unstated.

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 a single required parameter with 100% schema description coverage, including an example id format, so the schema does the heavy lifting. The description adds no format, validation, or lookup semantics for report_id beyond what the schema already provides.

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

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

The description states a specific verb and resource: check that a MusicCheck report id refers to a real screening and report what it concluded. That is distinct from retrieving a screening for internal use, but it never names get_screening or otherwise differentiates itself from the sibling that also takes a screening/report identifier.

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

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

It gives a concrete usage context — anyone can verify a report someone else shows them, e.g. a claim of 'already cleared' — which tells the agent this is the tool for third-party authenticity checks. It stops short of naming alternatives (get_screening) or stating 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.