record_suggestion

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

With no annotations, the description carries the full burden and addresses key behaviors: upsert semantics ('refreshes an open suggestion, never resurrects a dismissed/done one') and confirmation details (id, status, whether written or untouched). It does not cover permissions or side effects, but these are not critical for this tool.

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 two sentences, front-loaded with the primary purpose, followed by a concise explanation of key behaviors. Every clause adds necessary information—no filler or repetition.

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 lack of output schema and annotations, the description covers the essential aspects: purpose, dedup behavior, and the nature of the confirmation response. It does not explain return structure in detail, but it indicates what the confirmation reports, which is adequate for a straightforward write operation.

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% with each parameter clearly described. The description adds value by explaining that 'kind + dedupeKey' drive the upsert logic, which the schema alone does not convey. This complements the schema without redundancy.

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 clearly states the tool's purpose: 'Persist an actionable suggestion for the user' with a specific verb and resource. It also differentiates from siblings like list_suggestions (read) and record_outreach (different resource) by noting the Web UI dashboard context and the 'user-only action' reservation.

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 a clear usage criterion: 'Reserve for actions only the user can perform.' This tells the agent when to use it, distinguishing from system‑level actions. It does not explicitly name alternative tools, but the guidance is sufficient for the intended use case.

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