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

Annotations declare readOnlyHint=true, so the read-only nature is already captured. The description adds meaningful context about the metric's scale and output structure (resonance score, material origin, etc.), but does not disclose additional behavioral traits such as authorization needs, rate limits, or side effects. This aligns with the annotations without adding extra behavioral transparency.

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 well-structured, starting with the core purpose and followed by metric examples, input/output details, and use cases. It is front-loaded and informative, but contains some redundant phrasing (e.g., 'Colour Memory's proprietary semantic metric' and the output list) that could be tightened without losing clarity.

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?

Given the tool's complexity (proprietary metric with a defined scale) and the presence of an output schema, the description adequately explains the metric's levels (1.00, 0.80, 0.50), input requirements, and output fields. It also lists appropriate use cases. However, it does not address edge cases, error handling, or validation, leaving some gaps for a complete picture.

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 100%, with both parameters ('entries' and 'score_basis') described. The description reiterates the input structure and elaborates on output fields, adding marginal value. Since the schema already provides clear parameter meaning, the description's extra detail is helpful but not essential, aligning with the baseline score of 3.

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 clearly states the tool's specific purpose: a proprietary semantic metric scoring alignment between material origin and social consequence of a colour. It distinguishes itself from palette generators and lists specific use cases (investigative reports, forensic briefs, museum content, editorial PDFs), making the purpose highly specific and actionable.

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 description provides context for when to use the tool (e.g., investigative reports, forensic briefs) and implies uniqueness by stating 'This is the metric that separates Colour Memory from palette generators.' However, it lacks explicit guidance on when not to use it or how it differs from sibling tools like 'colour_story' or 'colour_forensics'. The omission of alternatives slightly reduces the score.

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