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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds that it returns 'problems and the Unlike line', which tells the agent the output is a verdict rather than a bare boolean. It does not explain what happens with an empty history, how strict the checks are, or where history comes from (that detail lives only in the schema).

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?

It is compact and front-loads the check itself, with no filler sentences. But the single semicolon-chained sentence packs four distinct rules and three undefined domain terms together, making it hard to parse rather than genuinely concise.

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?

For an 11-parameter tool with no output schema, the description leaves important things unexplained: what a 'recipe' is (the only required input), what 'the sheet' and 'Unlike line' mean, and what the returned 'problems' look like. An agent can infer the spirit of the check but not how to correctly supply the required input or interpret the result.

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 low at 27%, but the description does pick up much of the slack by naming how direction, hero, effect, work, footer, shape, and frame are each compared, giving real semantic grounding to seven of the eleven parameters. The required 'recipe' parameter and 'product' are never explained, and the 'history'/'reuse' behavior is left entirely to the schema.

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 states this is a uniqueness check and enumerates the specific comparison rules (direction/hero/effect vs recipe, two of hero/work/footer vs related group, shape vs last two, frame vs last three), which is concrete. However, it is framed in unexplained domain jargon ('Recent picks', 'the related group', 'the sheet', 'Unlike line') and never differentiates itself from siblings like pick_direction or the audit_* 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?

There is no statement of when to call this versus pick_direction, get_recipe, or audit_slop, and no preconditions (e.g., must a pick exist first?). The schema's 'reuse' field hints at an alternate mode, but the description never tells the agent when that mode applies.

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