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

Beyond the annotations, it discloses that edits mutate the original score, that the operation costs no credits, and that comment retries are unsafe after a lost reply — the last point usefully reinforces idempotentHint=false with a concrete failure mode. It still doesn't explain permission requirements or what a successful response looks like, but the added context is substantive.

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?

Four short sentences, front-loaded with the core capability, with no padding. 'No credits' is terse to the point of mild ambiguity (no cost incurred? credits not required?), which is the only weak spot.

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 multi-action tool with a nested payload object and no output schema, the description covers purpose, mutation semantics, cost, and a retry hazard. The remaining complexity (versions/parts modes, pagination behavior) is carried adequately by the fully documented schema.

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%, so the schema already documents share_id, action, limit, offset and the payload shapes. The description mentions only read/edit/comment while the enum also supports comments, versions and parts, adding no meaning beyond the schema and slightly under-representing the action 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 specific verbs (read, edit, comment) against a specific resource (a score shared with you), so scope is unambiguous. It does not name the closely related siblings (get_shared_score, save_shared_score, annotate_score), so an agent must infer which tool handles shared-score collaboration versus general score editing.

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 'a score shared with you' implicitly scopes usage to invited shares and excludes owned scores, and 'Do not retry comments after a lost reply' is an explicit operational rule. However, there is no explicit when-not guidance and no named alternative for plain reads or edits of owned scores.

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