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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-structural behavior: usage is recorded as a side effect, and the server resolves the published version of the skill rather than any draft, which materially affects expectations. It stops short of saying what the recorded usage entry contains or whether repeated calls are deduplicated.

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?

Five short, front-loaded clauses in a predictable pattern: purpose, use-when, do-not-use, next step, limits, example. No sentence is redundant, and the most decision-relevant information (purpose and trigger) comes first.

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 two-parameter, non-destructive tool with no output schema, the description covers trigger, exclusion, side effect, version constraint, follow-up calls, and an argument example. An agent can invoke it correctly without consulting anything else.

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 100% and both parameters are self-documenting ('ID of the skill being used', optional context string). The description adds only a format hint via the {"skillId":"uuid"} example, confirming UUID form, but says nothing about what 'context' should contain or how it is consumed, so this sits at the baseline-plus level.

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 first sentence gives a specific verb plus resource ('Read and record use of one approved skill') and scopes it to a single, approved skill. It implicitly separates itself from skill_list via the 'Use when skill_list shows a matching recipe' clause, but never names the nearest sibling, skill_get, so the read-vs-record distinction from that tool is left to inference.

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?

It states a positive trigger ('Use when skill_list shows a matching recipe'), an explicit exclusion ('Do not use when you need to publish or edit a skill'), and a prescribed follow-up sequence (workflow_apply_edits, then workflow_validate). That is the full when/when-not/next-step triad an agent needs to route correctly.

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