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

Annotations already declare readOnlyHint, idempotentHint and a closed world, so the safety profile is covered. Beyond that, the description discloses the two distinct response shapes ({results, count} vs {answer, sources}) and the important edge behavior that answer mode explicitly reports when FlowState has nothing rather than returning empty silently.

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 extremely tightly packed, with the core purpose first and the return shapes last, and no filler sentences. The telegraphic fragment style ("query + answer=true:", "No query: the newest records") is efficient but occasionally reads more like notes than prose.

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 an eight-parameter tool with no output schema, the description covers the critical decision branches and even sketches the return payloads, with annotations handling the safety profile. Remaining gaps are minor, such as the meaning of mode=auto and the default/max limit behavior, both of which are adequately handled by the schema itself.

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 all eight parameters are already documented in the schema, which sets the baseline at 3. The description does add real meaning beyond the schema, notably the shorthand record-id query syntax ("D12") and the interaction between query, answer and no-query states, but it leaves mode, project and since_hours semantics entirely to 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?

The description opens with a specific verb ("Find") and enumerates the resource types it covers (todos, decisions, changes, learnings, problems, solutions), which maps directly onto the content_types enum. It also distinguishes itself from the manage_* mutation siblings by stating "Read-only" and routes overview intent to start_here.

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?

It gives explicit mode selection rules: bare query means ranked matches, query with answer=true means a quoted answer, an id-like query returns one record in full, and omitting query lists the newest. It names start_here as the alternative for overview, but says nothing about when to prefer the manage_* siblings for listing or mutating records.

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