fidelity

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

No annotations provided, so the description carries the full behavioral burden. It adds useful output semantics (row/column layout, what the comparison reveals) but omits whether it is read-only, whether it requires installed mappers or exact prerequisites, cost/perf, and output encoding. Some value added, meaningful gaps remain.

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 dense sentences, action-first, with the output structure front-loaded right after the verb. Minor jargon ('Exceptional Value') adds cognitive load but every clause earns its place.

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 a nested object (mappings), no output schema, and no annotations, so the description should do more — yet it gives no return encoding, error behavior, or mention of how mappings/directory interplay works. Adequate conceptually but incomplete for this complexity.

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 parameters and the ct_id/directory exclusivity are documented in the schema itself. The description adds nothing about parameter behavior, so the baseline of 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 action: run every installed mapper on one record and compare per-target handling of Exceptional Values. The output shape (one row per EV, one column per target) makes the resource concrete. It doesn't explicitly name a sibling like map_record for contrast, so it falls just short of a 5.

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?

Implied usage is clear from the comparison framing — you'd use this to see how various formats represent missing/unusable values. However, there is no explicit when-to-use versus map_record/check_mapping, and no stated preconditions (mappers must be installed).

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