instant_estimate

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

Goes well beyond the readOnly/idempotent annotations by disclosing the validity envelope (refuses outside solved ranges), the physics assumptions (linear elastic, plane strain for thick_cylinder, plain tension for shafts), exactly how supports and loads are applied, and that 'the error bar covers the numerics, not the real part'. These are precisely the caveats that prevent a wrong answer being trusted.

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?

Front-loaded with the one-line what-it-is, then the contract caveats, then the per-shape key tables — a sensible order. The semicolon-dense enumeration is telegraphic and takes effort to parse, but given the schema provides no field documentation, every list item earns its place.

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 surrogate tool with nested object params and no output schema, the description covers inputs, assumptions, and failure behavior well, and hints at returns ('error bar (mesh + interpolation)', dimensionless-only answers when size is omitted). It stops short of naming the actual response fields, which the agent lacks elsewhere, and never explains `language`.

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?

With 0% schema description coverage, the description carries the full load and does so thoroughly: it enumerates the exact ratio keys for all seven shapes, marks nu as omittable with default 0.3, lists the per-shape size keys, and explains the consequence of omitting size. The only omission is the `language` parameter (ja/en/zh, default ja), which is never mentioned.

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 and resource ('peak stress or deflection of a standard shape in milliseconds') plus the mechanism ('Gaussian process fitted to points Studio solved and checked'), which is far more than the name conveys. An agent can immediately tell this is a fast surrogate lookup rather than an FEA run.

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?

Gives concrete routing rules: 'No case, mesh or solve', 'Refuses outside the solved ranges', and an explicit alternative for one case ('for open or capped ends run a simulation'). It does not, however, position itself against the sibling surrogate_predict or run_simulation in general terms, so the agent must infer the broader when-to-use boundary.

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