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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety behavior is fully covered. The description adds genuine value beyond that by pinning data provenance and version (2026-11-03) and by disclosing the returned fields in the absence of an output schema. It says nothing about result volume, ordering, or what happens with an empty/no-match search.

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?

It is a single compact sentence with no filler; every clause names either the dataset, its provenance, or a returned field. The structure is slightly list-heavy inside one sentence and 'each model's page' is left vague, but nothing is wasted.

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 field enumeration is the right thing to include and it is present, along with data freshness. What is missing is behavioral completeness: how results are ordered, whether the whole catalog is returned unfiltered, and how this discovery tool hands off to the estimation siblings.

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 the single 'search' parameter already carries an example-bearing description, so the baseline of 3 applies. The tool description never references the search parameter at all, adding no meaning beyond the schema.

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 resource (open-weight LLMs verified against config.json) and enumerates the fields returned (id, size, attention design, context, licence, memory at Q4/8k, model page), so the agent knows exactly what a call yields. It does not explicitly distinguish itself from siblings like what_fits or estimate_vram, though the catalog-listing intent is unmistakable from the field list.

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?

Usage is only implied: the 'search' parameter's own description shows filtering by model name or memory size, suggesting this is the discovery entry point before estimate/what_fits calls. The description never states when to use this versus what_fits, can_i_run, or estimate_vram, nor does it mention that no filtering returns the full catalog.

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