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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds a genuinely non-obvious behavioral trait: it never throws on ambiguity, it always returns candidates and delegates selection to the caller. That contract detail is not derivable from the annotations or schema.

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 short sentences, front-loaded with the action and input forms, then the return contract. No filler and nothing redundant with the schema.

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 one-parameter resolver with no output schema, the description covers what goes in and what comes back conceptually (candidates). It omits candidate shape/fields and the empty-result case, but the essential contract is present.

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% for the single query parameter, so the description carries the burden and does so well by listing the four acceptable identifier forms (partial ID, display_id, slug, dysfunction name). It doesn't mention the 256-char bound or the non-whitespace pattern, but those are edge constraints rather than semantic gaps.

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 states a specific verb (canonicalise) and enumerates the exact resource forms accepted (partial ID, display_id, slug, dysfunction name), so an agent knows precisely what it does. It does not explicitly contrast itself with siblings like get_dysfunction or list_dysfunctions, which is the only thing keeping it from 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?

Usage is implied rather than stated: it is clearly the lookup step to run before tools that need a canonical ID, and 'caller picks' hints at the follow-up decision. But there is no explicit when-to-use, no named alternative, and no statement about what to do if zero candidates are returned.

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