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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description doesn't need to repeat those. It adds critical behavioral context beyond annotations: the tool never infers facts not verified; filters narrow to confirmed facts (e.g., requireHipaa:true). It clarifies that ranking is by entry price with quote-only last, and that output includes source. This is valuable context that aligns with and extends the annotations without contradiction.

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 detailed but compact, front-loading the core purpose and output before diving into filter mechanics. Every sentence adds value: the first sentence defines behavior and output; the second explains filters; the third covers default behavior; the last mentions never inferring facts. It's slightly verbose due to examples but still efficient for a tool with 5 parameters and complex ranking logic.

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?

Given the tool's complexity (ranking, filters, verified facts, 275 themes), the description covers most essential aspects: how to select section (via list_sections), how filters work, what output format includes, and the verification principle. Minor gaps: no mention of pagination or result limits, and no description of error handling when no vendors match. But given no output schema and the annotation coverage, it is sufficiently complete for correct invocation.

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% and each parameter has a description. The main description adds cross-parameter meaning: how conjunctive filters combine (requireHipaa + requireSoc2 are ANDed), how section is used (theme slug), and the example mapping 'best CRM for HIPAA' to section + filter. However, individual parameter semantics are already well-covered by the schema, so the description adds only marginal value beyond that. 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 uses specific verb 'answer' with clear resource ('best <theme> for <use case>' and 'cheapest <theme>') and details the exact output: vendors ranked by entry price with compliance facts, free-tier flag, and best-for tags. It distinguishes itself from siblings by focusing on ranked best/cheapest answers rather than generic search or comparison, and explicitly ties to list_sections for theme slugs.

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 provides explicit when-to-use guidance: answering 'best' or 'cheapest' queries, and when to use filters (conjunctive fact filters narrow to confirmed facts). It names the alternative list_sections for getting slugs and warns against assuming the old four-section set, which prevents misuse. It also states when to omit filters (rank whole theme by price). This is clear and actionable.

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