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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and 'Read only' merely restates that. Nothing is said about ordering, pagination, result size, or what states of pitch drafts are included — the kind of behavior an agent needs when listing.

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 sentence with the filter scope up front and the read-only note trailing; no filler, nothing repeated beyond a short safety restatement.

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 single-optional-param list tool with full read-only annotation coverage and no output schema, this is close to sufficient. Still missing: whether results are paginated, what a 'pitch draft' record contains, and what happens when candidateId is omitted (all drafts) — leaving the agent to infer return shape.

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 must carry meaning; 'optionally for one creator' is the only cue that the opaque 'candidateId' UUID parameter scopes results to a creator. That is a genuine add, but it is thin for a parameter whose name (candidateId) does not itself say 'creator'.

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 (List) and resource (pitch drafts) plus a scope qualifier (optionally for one creator). Among the many pitch-related siblings (pitch, pitch_edit, pitch_approve, pitch_reject, pitch_sent, pitch_replied), the plural 'List' verb cleanly signals this is the read-collection member, though the description never names an alternative to route against.

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?

'Optionally for one creator' implies the filtered vs unfiltered usage, and 'Read only' signals it is the safe inspection step. But there is no explicit when-to-use guidance — e.g. whether to call this before pitch_edit or pitch_approve, or how it relates to the other pitch_* siblings.

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