map_record

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

With no annotations, the description carries the full burden and does so well: it discloses the three validation outcomes (valid, valid-with-Exceptional-Values, refused), that a bad value is marked rather than fatal, that outputs may be written to disk, and that a log entry (with hash) is produced. It stops short of stating side effects like idempotency, overwrite behavior in output_dir, or the fact that a log record is persisted.

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?

Four tight sentences, front-loaded with the action, then the validation semantics, then the return payload, then the model-selection rule. No filler and no repetition of the schema.

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?

There is no output schema, and the description compensates by enumerating the return payload (output, coverage report, one-sentence limitation, log hash). For a six-parameter tool with a multi-step pipeline this is nearly complete; only error/refusal return shape and file-write side effects are left vague.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains model-resolution precedence ('the model is the one the record names unless ct_id or directory is given') and ties output_dir to the inline-vs-file return behavior. It does not explain what 'target' or 'mapping' mean beyond the schema, but the precedence rule is a genuine addition.

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 ('Map one Governed Data Record to one target format') with clear scope ('one... to one'). It does not, however, contrast itself with siblings like check_mapping or fidelity, so the agent must infer when mapping differs from checking or measuring fidelity.

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 implied by the verb, and the description explains the validation pipeline a caller will encounter. It never says when to reach for this tool versus check_mapping/fidelity, nor does it state prerequisites (e.g. that a target must come from list_targets — that detail lives only in the schema).

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