file_flag

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

With no annotations, the description carries the full load and does well: it flags the write nature, the human-approval requirement, and the exact content conditions that cause rejection. It does not cover idempotency, duplicate-flag behavior, or what happens to case state after writing, which are the remaining behavioral gaps.

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?

Front-loads the two most important facts (WRITE, needs approval) in the first clause, then adds the field guidance and refusal rules without padding. The fragmentary phrasing around finding/evidence is terse but readable.

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 needn't be described, and the description covers the mutation/approval profile and rejection rules. The unresolved gap is the four undocumented parameters, including flag_type, whose semantics and allowed values are unavailable anywhere in the definition.

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% across six parameters, so the description must supply meaning for all of them. It explains only two ('finding' = the pattern in one sentence, 'evidence' = the numbers behind it), leaving ocid, case_id, flag_type, and approved_by entirely undocumented in both places.

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: 'Add one flag to the case file,' which is concrete and tells the agent this creates an artifact rather than querying one. It does not explicitly distinguish itself from the sibling check_red_flags, but the write framing is clear enough to separate the two in most cases.

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 hard precondition ('needs human approval') and explicit refusal conditions (unknown ocid, wording that decides the award or declares wrongdoing), which functions as meaningful when-not guidance. It never names an alternative tool such as check_red_flags, so routing among siblings is left partly to inference.

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