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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description goes further by disclosing truncation of long records with a marker and by clarifying that a not-found error means a stale id rather than an access restriction. That error-semantics detail is context annotations cannot express.

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?

Front-loads the core action, then uses short labeled sections (WHEN, WHEN NOT, EXAMPLES, error note) with zero filler. Every sentence conveys a constraint or a failure mode the agent needs.

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 documentation is not required, yet the description still covers truncation, id provenance, and error interpretation. For a single-parameter read tool this is fully sufficient to call 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?

Schema coverage is 100% and there is only one parameter, so the baseline is 3. The description adds real meaning beyond the schema's terse 'An id returned by the search tool': the meeting:/doc: prefixes, the opacity of ids, and the prohibition on hand-constructing them.

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 (retrieve) and resource (full record) and explicitly maps the two id namespaces to two outcomes: 'complete meeting transcript (for meeting:… ids) or the full document text (for doc:… ids)'. This lets an agent distinguish it from search and search_meetings without opening a schema.

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?

Gives explicit WHEN ('after the search tool, to read a result in full before answering or citing') and WHEN NOT ('never construct one by hand; only use ids returned by search'), plus the remedy for the most likely failure mode. Nothing about selection 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.