fit_check

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

No annotations exist, so the description carries full burden. It discloses the algorithm (resolve weight, estimate KV-cache, compare against free memory) and return fields (fits, target, bytes). However, it does not mention potential network calls for provider lookup or permission requirements, which are minor omissions for a read-only check.

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 sentences front-load the main purpose, then detail the process and return values. No wasted words; every sentence contributes essential 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 explains return values (fits, target, bytes). Parameter count (5) with full schema coverage means schema handles details. The description is sufficiently complete for a non-mutating tool, though it could mention potential network dependencies.

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 description coverage is 100%, so the schema documents parameters. The description adds value by explaining behavioral aspects like sizeBytes overriding lookup, contextLength default (4096), and parameterSize overriding lookup for KV estimate. This goes beyond the schema but could detail provider enum options.

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 clearly states the tool determines if a model fits on local hardware, specifying the algorithm including weight resolution, KV-cache estimation, and memory comparison. It distinguishes itself from sibling tools like load_model or model_info by focusing on hardware fit check.

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?

The description implies usage for checking model fit before loading, but does not explicitly state when to use this tool vs alternatives (e.g., load_model, suggest_model). No when-not or alternative guidance is provided, leaving usage context ambiguous.

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