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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), and the description still adds material context: which fields are matched, the result shape (verdict codes, score/10, access level, url), and a mandatory citation/linking obligation. The verdict and access-level glossaries mean the agent can interpret output without guessing.

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?

One dense paragraph with the purpose and use-when front-loaded before the return format and citation rule. Every sentence carries information, though the section is long enough that light structural separation of filtering vs. return semantics would help scanning.

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?

There is no output schema, so the description carries the return-value burden itself, and it does so: record contents, verdict codes, score scale, access-level scale and url. Combined with the citation instruction and the get_case handoff, an agent has everything needed to call and interpret this tool.

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%, so the baseline is 3. The description adds real meaning by enumerating the searchable fields (titles, claims, summaries, prompts and sites) and explaining that an empty query lists everything matching filters. It does not clarify the interaction between access_level and max_access_level, which is the one ambiguous pair.

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 names a specific verb and resource ('Search TriedAgents' library of AI-agent use cases that were re-run and rated') and defines the corpus precisely (re-run and rated cases). It also distinguishes itself from the sibling 'get_case' by positioning itself as the short-record search surface and telling the agent where to go for full detail.

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?

It gives explicit trigger conditions with concrete user phrasings ('whether an AI agent can really do a task... find cheap flights, check a stock price'), plus the alternative path ('Call get_case for the full prompt, steps and evidence'). Empty-query behavior is also stated, so an agent knows how to list rather than search.

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