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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false; the description adds real behavior: profiling happens locally, the model only explains pre-computed facts, no code is generated or executed, and authorization is required before running. One point of friction is 'no external data sources' sitting alongside openWorldHint=true, though that most plausibly refers to inputs rather than the outbound OpenAI call. It does not explain limits of 'bounded' or whether data leaves the machine for the model step.

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, front-loaded with the core action and followed by the authorization constraint and exclusions. Slightly jargon-heavy ('bounded', 'computed facts') but no filler.

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 tool with a nested free-form payload, six undocumented parameters, and no output schema, the description covers the intent and safety posture but not the mechanics. An agent still cannot tell what 'bounded' means numerically, whether the model step sends data off-machine, or what the response contains.

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 0% across six parameters, including an untyped free-form 'payload' object with additionalProperties=true. The description only hints that payload contains CSV/JSON and that authorization is required, leaving allow_model_processing, payment_signature, skip_free_trial, request_id, and force_new_task entirely unexplained in both schema and prose.

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 concrete verb and resource: 'Profile bounded CSV/JSON locally and ask OpenAI to explain computed facts.' This clearly separates it from analyze_document and analyze_payment_offers by naming the input type and the local-then-model split. It stops short of naming a sibling outright, so it is a strong 4 rather than a 5.

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 prerequisite 'Requires explicit authorization' is useful and the CSV/JSON + 'bounded' framing implies the intended data profile. However, there is no statement of when to prefer this over analyze_document, nor any exclusion (e.g., what 'bounded' rules out), so usage must be inferred.

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