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

Annotations already declare a safe read-only, closed-world operation, so the description's job is to disclose the analysis behavior — which it does well by naming the normalizations applied, the resulting group/suggestion/parent-child/singleton outputs, and the spelling-only limitation. It stops short of describing output shape or ordering (e.g. how groups are sorted), but the behavioral profile is substantially richer than the annotations alone.

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-loaded with the verb and resource, and every clause carries distinct information about matching rules or outputs — nothing is filler. It loses a point for being a long comma-spliced run-on that forces the reader to untangle the grouping criteria, which could have been a short bulleted list of match types.

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?

With three optional params, full schema coverage, no annotations gaps and no output schema, the description must explain both accepted input and returned analysis — and it does, covering input format, match rules, keep-suggestions, parent/child pairs and singleton detection. The only real gap is that output structure must be inferred from prose rather than described as a shape.

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 baseline is 3, but the description adds genuine semantics the schema does not: 'tags and/or categories (or terms)' clarifies that the three inputs can be combined or substituted, and 'optionally with usage counts as term (12)' explains the inline count syntax the schema only gestures at. The `terms` parameter's role as a merged single list is also spelled out.

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?

Opens with a specific verb+resource ('Find overlaps in tags and categories') and then enumerates the exact analytical operations performed, which is far more concrete than sibling names like naming_check or check_naming_conventions. An agent can tell this is a term-deduplication tool rather than a conventions linter without opening the schema.

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 specifies the required input shape and notes that matching is spelling-based so 'true synonyms need a human', which implies a usage boundary. However, it never states when to choose this over check_naming_conventions, lint_token_names, or naming_check, nor does it give any precondition or exclusion rules.

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