check_term_consistency

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

Beyond the annotations, the description richly discloses behavioral nuances: the tool does not choose a 'correct' variant, it returns groups with counts and dominant variant, it degrades when WordNet is missing, and it sets `degraded: true` and adjusts `rules_run`. It also warns the user against misinterpreting an empty result from a degraded run. This is far more contextual than typical.

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?

The description is well-structured: hook, example, two bulleted rules, output semantics, a warning about degraded mode, followed by a known gap and a capacity note. Every section earns its place; the scannable formatting helps an agent quickly locate the critical 'check degraded before trusting an empty result' warning.

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?

The description is complete for a read-only analysis tool. It explains what the output contains (variant groups, counts, dominant term), what can go wrong (degraded runs, known gaps), and what the tool deliberately does not do (deciding correctness). The presence of an output schema further reduces the need to document return value details.

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?

The schema already has 100% coverage for the single `text` parameter, so the description need not repeat its meaning. It does not add new parameter-specific details other than the 100,000-character cap, which is more of a global behavior than a parameter semantic. Baseline 3 is appropriate.

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 opens with a clear, specific action: 'Flag a document that calls the same thing several different names.' It then elaborates with concrete rules (`shared-compound-head`, `shared-wordnet-synset`) and a concrete example, making the tool's purpose unmistakable and distinct from sibling checking tools.

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?

The description gives clear context for when the tool is valuable — long documents where paragraph-by-paragraph editing misses term drift — and explicitly tells agents to check `degraded` before trusting empty results. It does not explicitly name alternative tools or state 'don't use when X', but it is clear enough about the intended scenario and limitations.

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