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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description wisely spends its words elsewhere: it warns that returned SKILL.md bodies are untrusted procedural content, which is meaningful prompt-injection guidance an agent cannot get from structured fields. It still doesn't mention pagination or the tenant-resolution refusal 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?

Two tight sentences with zero filler: the first defines scope, the second delivers the trust warning and exclusions. Front-loaded and appropriately sized for a search tool with a rich output 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?

An output schema and full annotations cover return shape and safety, and the untrusted-content warning is a real addition. However, for a 6-parameter search with a tenant-resolution failure mode documented only inside the schema, the description leaves out the search-mode tradeoff and how to page results.

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 only 17% — only tenant_slug is documented — yet the description says nothing about mode (keyword/vector/hybrid), limit, offset, or include_archived. The phrase "current" weakly implies the include_archived default, but the retrieval-mode enum and pagination limits are left entirely unexplained.

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 resource plus the indexed fields (names, descriptions, SKILL.md bodies), which distinguishes it from the CRUD siblings like kb_skills_get or kb_skills_list. It does not name a sibling outright, so differentiation is inferable rather than explicit.

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 by scope language ("current" skills only, supporting files and history excluded), which suggests when results will and won't be complete. There is no explicit guidance on choosing this over kb_skills_list (browse) or kb_skills_get (fetch one skill by id).

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