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

The description adds several meaningful behavioral traits beyond the readOnly/idempotent annotations: it handles language-insensitively ('Matches every language and ignores accents'), returns relevance scores and matched fields, and implies that results are summaries needing get_* for full details. These details directly inform agents how to interpret the response and compose multi-tool workflows. It falls one point short of 5 because it does not address potential latency, sorting/ranking criteria, or behavior when the query matches nothing—though the abundant output schema partially offsets this gap.

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?

Four sentences totaling ~60 words cover purpose, behavioral traits, return value, and usage guidance—all efficiently packed. The most critical information is front-loaded, and no sentence is wasted or repetitive. It achieves high informational density without sacrificing readability.

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 a 100%-coverage schema, a full output schema, and safety-specifying annotations, the description needs to cover only the behavioral gaps—and it does. It explains the language-agnostic matching, ranked output, and follow-up pattern. It loses one point for not explicitly noting that some domains can be excluded via the 'domains' parameter (limiting results), though this is a minor omission given that the schema and default behaviors are self-explanatory.

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 description coverage is 100%, so every parameter already has a description (query, limit, locale, domains). The description adds one useful hint—'query in the user's own words'—which clarifies the expected style of the query parameter beyond what the schema says. However, it never directly addresses the parameters as the 'not relevant' list does, and most of the value here comes from the schema. Baseline 3 is appropriate given the high schema coverage.

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 a clear verb ('Ranked keyword search') and resource ('across the whole corpus'), then enumerates the corpus scope by domain. It explicitly differentiates itself from get_* siblings by explaining the tool is for questions rather than known identifiers: 'Use this before any `get_*` tool whenever you have a question rather than an identifier.' This specific, actionable differentiator—backed by sibling names—distinguishes it from every get_* alternative, satisfying the 'specific verb+resource' + 'distinguishes from siblings' criterion.

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 an explicit rule for when to use this tool versus the get_* family, telling agents to search first when dealing with a question, then follow up with get_* for full details. It names the alternative explicitly and gives a condition-based guideline that is not present in the annotations or schema. It could earn a 5 by also acknowledging the list_* siblings for exploration use cases, but the conditional rule provided is concrete and immediately actionable.

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