scf_evidence_file_write

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the description's '(destructive)' label mostly restates structured data. It does add the editor+ authorization requirement, which is genuine added context, but it says nothing about what review/revalidate return or about side effects like deficiencies being raised (that detail lives only in 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?

A single front-loaded sentence that lists the operations and ends with the dispatch instruction. No filler, no restatement of the title, and the destructive element is called out inline.

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 6-parameter, 3-mode write tool with no output schema, the description covers all modes and the required role. It does not explain return values or the mode-specific edge cases (e.g. the 410 per-window review case), but those are documented in the schema, so nothing critical is missing at the description layer.

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 100%, so every parameter including the method enum is already fully documented in structured data. The description's only contribution is signaling that 'method' is the discriminator, which is minimal added meaning over the enum descriptions.

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 names a concrete verb and resource ('Act on an uploaded evidence file') and enumerates the three actions it covers: approve/reject/request revision, re-run validation, and soft-delete. That is enough to separate it from the read sibling scf_evidence_file_read, though it never names that sibling explicitly.

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?

Usage is only implied: the agent is told to 'Pick with method' and given the list of operations, but there is no explicit when-to-use/when-not guidance or any routing statement versus scf_evidence_task_write or scf_evidence_write. The role hint '(editor+)' gives a precondition but not a selection rule.

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