delete_scan

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

With no annotations, the description carries the full burden and delivers: feedback is locally backed up first and deletion aborts if backup fails (reversibility/safety), the server injects random 2-5 s delays and runs one tool at a time so tools must never be called in parallel, and a concrete retry policy distinguishes never-retry errors (auth_expired, site_changed, unknown_state, internal_error, profile_in_use) from transient ones bounded at two retries. This is unusually rich operational disclosure.

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?

Purpose and the key anti-misuse warning are front-loaded, and every following sentence carries operational weight (backup, confirm, pacing, retry policy) rather than filler. It is dense with long parenthetical clauses, which costs a little readability, but nothing is expendable.

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 described. Given a destructive mutation with no annotations, the description supplies the missing safety profile, concurrency constraints, confirmation rule, and error recovery guidance — everything needed to invoke it correctly and safely.

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 compensate. It explains confirm meaningfully (required when deleting the latest result of the current loop, defaulting false in the schema) rather than restating the boolean, though scan_id's format/derivation is left to the agent (contextually obvious from list_scans). Strong compensation with a small remaining gap.

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+resource ('Delete a scan from My Scans') and immediately scopes it against a tempting but wrong interpretation ('NOT a way to get more scans'). This distinguishes it cleanly from siblings like list_scans and start_scan, which an agent could otherwise conflate with scan management.

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?

Explicitly frames the tool as 'optional history tidying' and warns when NOT to use it ('never plan on allowance_restored'), then adds a precondition (confirm=true for the latest result of the current loop) and an error-handling policy keyed to specific codes. When-to-use, when-not, and what to do on failure are all covered.

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