render_view

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds real behavioral context beyond that: output carries a colour bar, modal shapes are normalized to max displacement 1, omitted step means the last converged step, faces mode overlays numbered faces with highlights in an accent colour, and large deformation uses true scale. That is useful, but it is telegraphic and omits things like image size, what happens on an unsolved case, or error behavior.

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?

It is short and front-loads the output format, with no filler sentences. However the structure is a dense run-on of pipe-delimited tokens and parenthetical asides; the quantity list is hard to scan and the faces/mode/step rules are not separated visually. Compactness is achieved at the cost of parseability.

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 7-parameter, no-output-schema rendering tool, the description covers the ambiguous parts: which quantities exist, modal vs step semantics, face highlighting, contact and plasticity fields, and scale convention. The remaining gaps (view orientation, language of labels, case_id expectations, failure modes) are modest but real given the total absence of schema descriptions.

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 0%, so the description must carry parameter meaning, and it does for the highest-risk parameter: quantity is enumerated extensively by physics domain (structural, CFD, electrostatic, thermal) plus special values faces and mode. mode, step and highlight are also explained with defaults and semantics. view, language and case_id get no explanation at all, leaving three of seven parameters undocumented anywhere.

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 opens with 'PNG with colour bar', which identifies the output artifact, and the long quantity enumeration makes clear this renders field results of a case. Combined with the name render_view an agent can infer a rendering tool, but the description never states the verb+object in a single plain sentence (e.g. 'render a case result field as a PNG'). It does implicitly distinguish itself from get_results via 'Numbers: get_results.'

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 gives an explicit alternative for a different need: 'Numbers: get_results', which routes numeric extraction away from this tool. 'Empty = default' clarifies the no-quantity path, and the faces/mode/step notes explain the special modes of use. It does not state when-not to use it (e.g. before a mesh exists or before a case is solved), which keeps it below a 5.

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