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

Annotations already establish read-only, idempotent, closed-world behavior, so the description's job is to add return-shape and workflow context — which it does by listing slug, size, context length and licence and explaining the slug handoff. It does not disclose the limit/default or any ranking or pagination behavior, leaving a minor 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?

Two tight sentences: the first defines what it searches and what it returns, the second routes to the follow-up tool. Every clause carries information and the key scope is front-loaded.

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 appropriately summarizes return fields, and annotations cover the safety profile, so an agent has nearly everything needed. The unexplained limit/default and lack of ordering or pagination detail are the remaining, modest omissions.

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 only 33% (query alone is documented), so the description needs to compensate. It clarifies that matching is by name or task and lists the task vocabulary, but the enum values are already in the schema and it never explains the limit parameter or its default. Partial compensation only.

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 and resource ('Find open-weight AI models') and enumerates the task categories it matches on. The hardware-oriented siblings make the resource distinction obvious, and naming hardware_for_model ties it into the surrounding toolset.

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?

Clear context for when to reach for it (looking up models by name or task) and it points to the follow-up call (hardware_for_model with the returned slug). It gives no exclusions or caveats about when another approach is preferable, but no competing model-search sibling exists.

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