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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds genuinely non-obvious session semantics — a loaded skill 'stays loaded for the conversation' and must not be re-loaded — which is operational context beyond the structured hints. It loses a point only for not clarifying error behavior or what happens if an id is invalid.

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 core purpose in the first sentence, then guardrails. The trailing imperatives ('Do not write from a catalog line. Do not poll.') are terse and earn their place as failure-mode prevention, though there is mild repetition of the load-once rule.

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-param read tool with full schema coverage, no annotations gap, and no output schema, the description covers purpose, batching, timing relative to writes, and session lifetime. 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 description coverage is 100%, so both skillId and projectId are already documented, including the comma-separated syntax and the null-falls-back-to-open-project rule. The description reinforces the comma-separated example but adds no parameter meaning the schema lacks. Baseline 3 is correct.

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 ('Load the full body of AI Skills by skillId') and immediately contrasts it with the sibling catalog ('The system prompt catalog is titles only. It is not the body.'). An agent can distinguish this from read_film or patch_film without opening a 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?

Explicit when-to-use and when-not-to-use: batch all needed ids in one call, load each named skill 'before the first write that needs it', never reload a loaded skill, and don't load unneeded skills. It even names the sibling writers (patch_film, replace_component, scaffold_component) that signal a load is required.

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