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

Annotations already declare readOnly/idempotent/non-destructive/non-openWorld, so the safety profile is handled. The description still adds real behavior: results are a partial selection rather than a complete set, which shapes how the agent should follow up. It doesn't cover latency, auth, or response shape, keeping it short of a 5.

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?

Three sentences, zero filler, front-loaded with purpose before the invocation constraint and the sibling alternative. Each sentence 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?

An output schema exists, so return values need not be explained, and annotations cover safety. The description fully covers purpose and routing; only the semantics of projectId and limit are left implicit, a minor gap for an otherwise self-explanatory read 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 description coverage is 0%, so the description must carry parameter meaning; it clarifies only `request` (brief scene/topic query, not a transcript) and says nothing about projectId or limit. That is meaningful compensation for one of three parameters but leaves the rest undocumented.

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 precise resource set (canon, recent approved scenes, latest provisional checkpoint), plus the triggering situation (continuing a saved story or recovering it in a new chat). An agent can distinguish it from siblings like search_story_canon or get_canon_history without opening the 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 the when explicitly ('before continuing a saved story or recovering it in a new chat') and names the alternative with its selecting condition ('use search_story_canon for specific missing facts'). It also warns that results are a selection, which tells the agent not to expect exhaustiveness.

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