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

Annotations already declare readOnlyHint=true, so safety is covered, but the description adds real behavioral context: the id format ('<group>/<slug>', what fabrement_icon() takes), the meaning of colorMode values for CSS painting, the presence of a usedBy field, and the availableTags field. It does not mention pagination, result caps, or ordering, which is the only remaining gap.

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?

Highly front-loaded — the field list and the sibling distinction come first, prerequisites last. The telegraphic register ('No markup — get-icon for that', the 'second arrow' aside) is efficient but slightly compressed, and the field inventory is arguably schema-shaped rather than purpose-shaped.

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 carries the full burden of describing returns and does so comprehensively (id, name, description, tags, colorMode, url, usedBy, availableTags). Combined with the filter guidance and the mandatory skill-doc prerequisite, an agent has everything needed to call this correctly on the first attempt.

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 67%: tags and search carry inline descriptions, while group has an enum but no prose. The description does not explain how these three filters compose (AND semantics, substring matching) beyond what the schema says, and its mention of 'tags' refers to a return field rather than the filter parameter. Adequate but not additive.

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?

Opens with a specific verb+resource ('The site's icon library') and immediately enumerates the returned fields, so the agent knows exactly what this returns. It explicitly distinguishes itself from fabrement-get-icon ('No markup — get-icon for that') and is clearly the read-side counterpart to save-icon/delete-icon.

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 precondition ('List BEFORE drawing an icon or saving one') with the concrete failure mode it prevents ('a second arrow beside the first'), names the alternative tool for markup, and states a prerequisite skill doc to read before the first call. When/when-not/alternative are all covered.

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