Extract Behavioural Model

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

With no annotations, the description carries the full burden and does so well: it discloses this is a paid, mutating action only when confirm_estimate=True, that the requester is charged, that the estimate must be relayed to a human before confirmation, that the operation is queued and may take an hour, that polling is required, and that op... refusals return as {confirmed, http_status, code, message} with specific 409/402/404 semantics. These are exactly the behavioral traits an agent needs and that structured fields do not supply.

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?

The description is long but front-loaded and organized into a purpose statement plus two numbered steps followed by refusal handling. Given the multi-step, asynchronous and paid nature of the tool, most sentences earn their place; the heavy use of double-backtick code formatting and the dense refusal enumeration add some reading overhead.

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 complex, paid, asynchronous mutation with an output schema present, this is complete: it covers preconditions, both call modes, the queued job and its polling loop, the returned estimate fields and notices, downstream siblings to use, and every relevant error code including a permission-implication note for 404.

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 80%, so the baseline is 3, but the description adds real meaning: confirm_estimate=False estimates while True extracts, and set_revision/model_version are the values that must be carried forward from the estimate payload returned in step 1. The only parameter left unexplained is server_version, which the description also ignores.

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 opening sentence 'Give a model that has no behavioural model one' states a specific verb (extract/give) and resource (behavioural model) with a clear scope restriction (only models that lack one). It distinguishes itself from the read-only sibling get_behavioural_model, which the description explicitly points to when the 409 has_behavioural_model refusal fires. An agent can separate this from edit_behavioural_element/confirm_behavioural_model without opening schemas.

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 lays out an explicit two-step protocol: first call with confirm_estimate=False, relay the estimate to the person, then call with confirm_estimate=True and the returned values, and it explicitly forbids confirming on your own. It also names alternatives via the refusal codes (poll with get_behavioural_model, read proposals with get_behavioural_links) and the condition under which each applies.

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