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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds valuable behavioral nuance beyond that: 'oftenMeans' is 'a labelled heuristic, never a conclusion.' It also conveys that the tool exposes a fixed, closed vocabulary of 7 shapes and 33 forms, which helps the agent calibrate expectations about what it will receive.

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 compact at three sentences, but the first sentence nearly repeats the title verbatim, providing little additional value. The second sentence is conceptually rich but indirect, and the third delivers a genuine caveat. It is appropriately sized but not optimally efficient.

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 single optional parameter, the presence of an output schema, and read-only annotations, the description covers the essential context: what the vocabulary contains, the shape-to-form relationship, and the heuristic caveat. It could be more complete by explicitly stating the default behavior when no 'shape' filter is provided, but this is minor.

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%, so the single optional 'shape' parameter is already well-documented with an enum and a description. The description reinforces the conceptual role of shapes ('7 data shapes') but adds no syntax, filtering behavior, or value-specific guidance beyond what the schema provides. The baseline 3 applies.

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 identifies the resource precisely: 'The canonical form vocabulary' with '7 data shapes and the 33 canonical forms they resolve to.' The tool's purpose as a structural reference is clear. It does not explicitly use a verb like 'retrieve' or 'list,' and it does not directly compare itself to siblings, so it stops short of a 5.

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 implies usage context: canonical forms are the structure that lets one engine interpret cross-domain metric data, so an agent should consult this when needing the structural vocabulary rather than domain-specific rewrites. However, it never explicitly states when to use this tool versus alternatives or when it should not be used.

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