Evaluate suggestions

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

Description discloses that it returns 'newly created suggestions (may be empty)', implying a side effect, and the idempotentHint annotation helps clarify retry safety. It does not fully describe all state changes or error behavior, but the combination of description and annotation is fairly transparent.

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?

The description is compact and front-loads the core purpose and triggers. The phrase 'Core principle: silence is also a skill' is somewhat aphoristic but still adds meaningful usage guidance and does not feel like 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?

Given the moderate complexity and the presence of sibling tools, the description covers the main entry conditions, output nature, and constraints. It could be slightly stronger by explicitly distinguishing when to use suggest_list/suggest_accept/suggest_ignore instead, but it is largely complete for an agent to decide when to call.

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 covers 100% of parameters, and the description adds useful semantic detail for trigger values (session_end default, session_mid realtime strong signals only, manual). It reinforces the messages and sessionId purposes without contradicting the schema.

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?

Clearly states the verb 'Evaluate' and the resource 'proactive suggestions', with explicit examples of signals (unfinished todo, repeated mistake, follow-up promised, automation opportunity). It is easy to distinguish from sibling tools like suggest_list or suggest_accept because it focuses on deciding when to create suggestions.

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?

Provides concrete call conditions: when conversation signals are present, plus explicit constraints such as 'At most 1 per call', 'session budget limits', and 'none during do-not-disturb hours'. The guidance 'silence is also a skill' adds useful judgment context for when not to suggest.

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