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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is free; the real added value is the publication semantics (drafts excluded unless includeDrafts, marked status 'draft'), the org-policy constraint that drafts are dropped where only published skills are allowed, and the prerequisite that under controlled releases an admin must enable 'Agents read skills'. That is genuine permission/scope disclosure beyond annotations, though the description stops short of volume or ordering 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?

Front-loaded with the resource definition and a call-to-action, and nearly every sentence carries operational information. It is delivered as one undifferentiated block, and the usedSkills/traceability aside, while useful, sits far from the core list/read decision and lengthens the call.

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 zero-required-parameter read tool with full schema coverage, no output schema, and closed-world annotations, the description covers return shape, publication scope, draft handling, permission gating, and the downstream read/write tools. Nothing an agent needs to call it correctly is missing.

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 baseline is 3; the description still adds meaning by explaining that includeDrafts marks results 'draft' and that drafts may be silently omitted by org policy, and by defining tags as 'which name the document types it applies to', which clarifies the tag vs documentType distinction. The query and projectId filters are left entirely to the schema.

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 concrete resource and scope: 'Your organisation's skills: reusable instructions for agents, written and published in Traceable documents', then enumerates exactly what each item contains (skillId, name, description, tags, version, source document) and pins the source to the latest PUBLISHED version of documents in the caller's projects. It also separates itself from traceable_skill_read ('Load one with traceable_skill_read') and from the write path ('edit its [[skill]] row ... with the block tools'), so an agent can route correctly without opening any schema.

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?

Gives an explicit trigger ('Call this when you connect'), the follow-up action ('follow the published skill whose description matches the task'), and the alternative tool for retrieval. It also covers the write-side alternative and when includeDrafts matters, plus the org-policy exclusions that change what comes back.

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