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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real context beyond them: a 30-minute cache, the ~750 row magnitude, value units in cents computed over priced members only, and null avg_value semantics when nothing is priced. It does not warn about response size (icons embedded per member across up to 200 rows per page), which is the one material omission for a read tool.

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 purpose and scope, then field semantics, then a slug-derivation note useful for follow-up calls; nearly every clause carries information. It runs long for a list tool and the slug paragraph, while helpful, is about a different endpoint.

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?

There is no output schema, and the description compensates fully by documenting the return shape field-by-field (name, count, total_value, avg_value, icons with {url, name}), units, null conditions, and cardinality. An agent can construct and interpret the call without opening 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 the sort enum is already documented in the schema, so the schema carries the parameter burden. The description clarifies value semantics ('cents, over the priced members only') which does aid interpretation of value_* sorting, but it adds nothing about page/per_page behavior; baseline 3 applies.

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 names the resource and its full scope ('Every skin collection (about 750)') and enumerates the returned fields, so an agent knows this is an exhaustive listing rather than a lookup. The reference to GET /skins/collections/{slug} implicitly points at the singular detail sibling, but get_skin_collection is never named, so differentiation is inferential 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 only implied: the phrase 'Every skin collection' suggests bulk enumeration versus a single-collection fetch, but there is no explicit 'use this when / use get_skin_collection instead when' guidance. With 35 sibling tools including search_skins and get_skin_collection, an explicit routing sentence would have earned a higher score.

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