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

Annotations only supply destructiveHint=true, so the description carries most of the behavioral burden and does well: it discloses the non-streaming constraint and the per-token billing model, both real behavioral traits a calling agent must account for. It does not contradict the annotation; it simply omits return-shape details.

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 short sentences, front-loaded with the core action and constraint, with zero filler. Each sentence earns its place by adding a distinct fact (what it does, streaming behavior, endpoint routing, underlying API).

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?

For a 10-parameter inference tool with no output schema, the description covers the essentials an agent needs to invoke it correctly (billing, non-streaming, endpoint addressing). It does not describe the response shape or sampling-parameter tradeoffs, but those are standard for a chat-completions API.

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 60%, so the schema handles most parameters, but the description adds genuinely non-obvious meaning for 'model' by explaining the `<project_slug>/<endpoint_slug>` form used for dedicated endpoints. The remaining sampling parameters (temperature, top_p, seed, etc.) are left to 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?

States a specific verb+resource ('Run a chat completion on a Together model') and immediately distinguishes itself from siblings like together_create_embeddings and together_generate_image by naming the exact modality. The scope qualifiers ('Non-streaming', billed per token) sharpen the purpose further.

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 gives practical routing guidance ('For a dedicated endpoint pass its `<project_slug>/<endpoint_slug>` as the model'), which is useful for choosing between a shared model and a dedicated endpoint. However, it never states when to use this tool versus alternatives or any exclusions, leaving that to inference.

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