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

Discloses the auth requirement, the exact scope of destruction (brief plus its results), and the default lifecycle ('deleted after the last page is read, or after an hour idle') — all context the annotations do not carry. The only wrinkle is that the description reads as an irreversible destructive action while destructiveHint is false; the lifecycle note largely reconciles this (the data is ephemeral regardless), so it is a tension rather than a flat contradiction.

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?

Two sentences, no filler, with the access constraint front-loaded before the action and its lifecycle note parentheticalized. The auth preamble does slightly delay the core purpose statement, but it carries genuine routing value.

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 a one-parameter, no-output-schema tool this covers purpose, auth, destruction scope, and default expiry — nearly everything an agent needs. It omits failure behavior (e.g., what happens if the brief_id is unknown or already expired), the only meaningful remaining gap.

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?

With 100% schema description coverage on the single brief_id parameter, the schema already explains its provenance ('the brief_id brief_upload returned'). The description adds no format, validation, or error semantics for that parameter, so the baseline 3 applies.

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 ('Delete an uploaded brief and its results') with explicit timing ('from the server now'), which distinguishes it from read-oriented siblings like get_brief_results and check_brief. An agent can identify this as the immediate-cleanup action 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 a clear prerequisite ('Signed-in accounts only') and routes anonymous callers to a named alternative ('use check_brief with text'), which is real when-to-use guidance. It stops short of saying when an agent should delete early versus simply letting the brief expire, leaving that inference to the reader.

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