Compare the results of AI plans

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

Annotations cover the safety profile (readOnly, non-destructive), freeing the description to disclose rich domain behavior: ranking by interactions per measured post rather than total, ranked-only eligibility (3+ measured posts), maturing-plan caveat, and 'missing metrics are not zeros'. These are non-obvious semantics an annotation could never convey.

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 core question and tool purpose, then flows into ranking rules and filtering guidance. Information-dense and mostly waste-free, though slight redundancy between 'compare plans fairly' and 'pass one social_network' costs a point.

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 8-param comparison tool with no output schema, the description covers purpose, ranking semantics, eligibility rules, maturation caveat, range filtering, fairness advice, and missing-data handling. Nothing material is missing despite the absence of a return schema.

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 75%, above the 80% threshold band boundary, so the baseline is 3. The description adds semantic context for range ('filters on the week the plan published in') and social_network ('compare fairly across networks'), but doesn't disambiguate sort options or other params beyond 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?

States a specific verb+resource: comparing AI plan results and determining which template works best, framed by the actual user question ('which of my AI plans did best?'). Distinguishes itself from siblings like list_ai_plans and get_ai_plan by focusing on comparative performance.

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?

Gives clear application context ('which of my AI plans did best?') and explicit fair-comparison advice ('pass one social_network'). Does not name excluded siblings or state when not to use it (vs. list_ai_plans), so it falls short of 5.

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