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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is covered. The description adds real behavior not in the annotations: dated-variant resolution and the explicit not-found contract ('found:false with the closest names, never an empty result'). Auth/rate-limit context is absent but not essential here.

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 sentences, front-loaded with the verb+resource, then the matching and error behaviors. No filler sentences; each clause carries distinct information.

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 carries the burden and does so: it lists the returned fields (organization, release date, parameter count, compute, hardware, accessibility) and describes the negative/edge case result. Nothing essential 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, but the description adds genuine semantics beyond the schema: name matching tolerates dated variants (e.g. 'GPT-4' resolving to Epoch AI's 'GPT-4 (Mar 2023)' row), which tells the agent how loosely to format input.

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?

Specific verb ('look up') plus a single, well-defined resource ('one AI model in Epoch AI's models database by name'), and it enumerates the returned fields and the dataset provenance. The 'one model' framing implicitly separates it from the sibling ai_models_search list-style tool.

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 clear context for a single-model name lookup and notes the fuzzy-match behavior, but never states when to prefer this over the sibling ai_models_search or when not to use it. Usage is implied rather than routed.

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