gaps

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

The description discloses a critical caveat beyond the readOnlyHint and idempotentHint annotations: the ranking is triage, not measurement, because the log only records how searches went, never whether answers helped. This protects the agent from over-trusting the output.

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?

Two dense, front-loaded sentences: the first describes the output and ordering; the second tells when to invoke and how to interpret the ranking. Every clause earns its place.

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?

Complete for a read-only triage tool: it explains purpose, usage trigger, output ordering, and interpretation limits. It stops short of explicitly naming sibling alternatives or the precise returned shape, but overall covers the agent's key needs.

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%, with both limit and since already described clearly. The description adds useful context around interpretation but does not need to add parameter-level detail.

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 ('Report') and a specific resource ('what this knowledge base is repeatedly asked and answers badly'), with a clear output ordering ('worst first'). This clearly distinguishes it from sibling retrieval tools like search or retrieve.

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 an explicit usage trigger: 'Call it to decide what to learn next.' It does not explicitly contrast with sibling tools or say when not to use it, but the intended decision point is clear enough to guide an agent.

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