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

Annotations already establish readOnlyHint=true and openWorldHint=false. Beyond that, the description discloses meaningful behavior: data is cross-checked against the pack's own files at a pinned commit, and the author's stats are explicitly flagged as reported rather than verified. That provenance detail is exactly the kind of trust signal an agent needs; only the response shape is left implicit.

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?

It is front-loaded with the resource and ends with the actionable routing sentence, so the structure is sound. However, the middle is a single sprawling clause listing eight card contents in a row, with a parenthetical and a stray ellipsis, which makes it dense to parse rather than efficient.

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?

With no output schema, the description must convey what comes back, and it does so thoroughly by enumerating the card's sections, including security-relevant ones (hooks, files written, network access). What is missing is only minor: the granularity of the per-skill list and whether uninstall instructions are always 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 coverage is 100% and the schema's own example (DietrichGebert/ponytail, ponytail-review) documents the accepted identifier forms. The description only implies that the argument identifies a pack or skill and does not add resolution rules or fallback behavior beyond that. Baseline 3 applies when the schema carries the parameter burden.

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 resource and scope: the detail card for one Agent Skills pack, verified against the pack's own files at a pinned commit. It enumerates the card's contents (purpose, per-skill file mutation, install/uninstall commands, local execution surface), which distinguishes it from the sibling find_skills. The jargon 'AgentGid card' adds a little noise, but the substance is unambiguous.

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?

The closing sentence gives an explicit workflow: search with find_skills, then call get_skill before installing a pack, naming the sibling to use instead for discovery. The 'before installing' framing supplies the triggering condition, not just a vague suggestion.

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