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

Annotations already provide readOnlyHint=true and idempotentHint=true, but the description adds critical behavioral context: the 24-hour lifetime, failure semantics (expired or never written), and that no authentication is needed. This goes beyond the hints, albeit not significantly; score reflects strong transparency but not perfect depth.

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 concise and front-loaded with the core purpose in the first sentence. Subsequent sentences add essential error handling and authentication context. Every sentence contributes value, though slightly longer than necessary.

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 there is an output schema, the description need not explain return values, and it doesn't. It covers key context: provenance (previous store call), lifetime (24h), and failure mode. It could mention what the value looks like (but output schema does) and any rate limits, but overall adequate for a simple 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?

The schema fully describes storage_id with a description ('The UUID that store_temporary_data returned.'), so parameter semantics are already covered. The description adds no extra parameter-level detail, but since coverage is 100%, a baseline of 3 is appropriate.

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 retrieves a JSON value stored by store_temporary_data, specifying the resource (temporary data) and the action (read/fetch). It distinguishes from siblings like read_webhook_capture and read_human_approval by focusing on temporary data and referencing its companion store tool.

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?

The description explicitly explains when to use the tool: to retrieve previously stored temporary data, and when not to retry on failure (since failures indicate expired or never-written IDs). This guides the agent to avoid unnecessary retries, which is crucial behavioral guidance, even though it does not name alternatives directly.

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