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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real value beyond that: it discloses cost characteristics (cheaper than MusicXML) and side-effect absence (nothing is re-recognised), plus interpretation semantics for key vs keyName/mode.

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

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

Two compact sentences with no filler; the content list is front-loaded and the key/keyName caveat follows as a targeted clarification. Slightly awkward opening ('What is in a recognised score') is a minor structure cost but the text earns its length.

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; the description nonetheless clarifies the one ambiguous field pairing (key vs keyName/mode). Combined with the cost/side-effect hints, an agent has enough to call this correctly, with only the `file` collection-mode usage left implicit.

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

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

Schema description coverage is 100%, so both parameters (file, recognition_id) are fully documented in the schema. The description adds nothing about parameters – notably it never explains the collection-mode `file` selector – 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?

The description enumerates exactly what a recognised score returns (title, composer, key, time signature, tempo, duration, per-part name/range/clefs/lyrics), which makes the resource and its payload unmistakable. It never states the verb outright (it describes contents rather than saying 'returns a summary of'), so an agent infers 'describe' from the name, but the resource is clear enough to distinguish it from export/get_musicxml siblings.

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

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

'Cheaper than reading the MusicXML' implies the trade-off versus get_musicxml, and 'nothing is recognised again' hints the recognition is already done. However, no sibling is named explicitly and there is no stated when-not condition (e.g. when you need the actual notation, use get_musicxml/export_score).

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