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

Annotations only declare readOnlyHint=true, but the description adds substantial non-obvious behavior: results are auto-scoped to the authenticated user, results are truncated and capped, and messages containing secret-shaped strings are silently dropped with a prescribed user-facing response. These are exactly the traits an agent could not infer from the schema.

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-loaded with purpose, then call conditions, then a Rules block — a clean, scannable structure. The three quoted example queries are useful for trigger matching but add length; nearly every sentence still earns its place.

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?

With no output schema, the description covers return characteristics (truncated, capped, secrets filtered) and the retry policy, which is what an agent most needs. It stops short of describing the shape of a returned message (content, timestamp, conversation id), a minor gap for a search tool.

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 baseline is 3, but the description adds real semantic guidance for `limit` ('do NOT ask for limit=20 unless the default 5 returned nothing relevant'), which encodes a retry/escalation policy the schema's min/max cannot express. It does not discuss conversationId, though the schema already explains it well.

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 and resource ('search the user's full conversation history') plus the underlying mechanism (Postgres full-text search). It also explicitly distinguishes itself from the closest conceptual sibling by declaring this to be FACTUAL recall and routing preference lookups to search_memory.

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 an explicit trigger condition ('when the user refers to specific past messages, errors, decisions, or details not in the live context window'), three concrete example utterances, and a named alternative (search_memory) for a different intent class. The Rules block further constrains limit escalation behavior.

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