production.uv_analyze_texel_density

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low; the description adds real domain behavior instead — the 32..8192 resolution bounds, per-tile resolution overrides, and the fact that results are reported as a distribution plus material-region density. That is meaningful context an agent would not get from the schema or annotations.

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 metric and its derivation, then limits and output shape. Nothing is redundant, though the semicolon-packed clauses are dense enough that the required-parameter story gets squeezed out entirely.

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?

Output schema exists and annotations cover the safety profile, so return format and mutation risk need not be described. The remaining gap is the opaque required 'relationship' parameter, which leaves the definition incomplete enough that an agent may not be able to invoke this correctly on the first try.

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%, so the description must carry parameter meaning and it does not: the required 'relationship' string is never mentioned, and 'options' (an arbitrary object) is only obliquely gestured at by 'resolution 32..8192, per-tile resolution overrides'. An agent cannot tell what 'relationship' expects.

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 metric ('Measure texels/metre') plus the inputs it derives them from ('world surface area and UV area'), which is far more informative than the bare name. It does not name or contrast with the nearest siblings (uv_analyze, uv_validate, retopology_analyze_density), so an agent still has to infer the boundary.

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?

Usage is only implied: this is the tool that quantifies UV density distribution rather than validating or generating UVs. The one genuinely useful interpretive cue is 'no universal density target', which tells the agent not to treat the result as pass/fail, but no alternative tool or precondition is named.

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