Search models

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses the credit-cost schedule, the offset-quadratic multiplier, and the default delisted-exclusion behavior. This is exactly the operational context an agent needs before issuing a deep query.

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?

Three tight sentences, front-loaded with purpose, then filters, then cost. No filler; the cost formula is dense but directly informs query design.

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 no output schema, the description still conveys the shape of a result set (rows, page sizing) and the cost/limit tradeoff. It could say a bit more about what each row contains, but nothing critical for correct invocation is missing.

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 baseline is 3. The description adds value by enumerating the filter axes (method, family, author, license, download range, creation date) and spelling out the delisted semantics (dead|all) that an agent must understand to avoid silently missing records.

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 (Search) on a specific resource (the abliteration.org catalog of abliterated/uncensored LLMs) and even names the backing endpoint (GET /models). It clearly distinguishes itself from get_model, search_datasets and the author/method listers.

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 concrete selection guidance: filter narrowly rather than paging deep, and explains that delisted models are excluded unless delisted=dead|all. It does not, however, name a sibling alternative (e.g. get_model) for retrieval by a known ID.

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