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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating. The description does add genuinely new behavior: results are masked and truncated to the top 25 rows, and the response also carries the underlying weight/filter definition. It omits what happens on an unknown or unpublished slug (error vs. empty) and any auth requirement, and the return shape is stated twice.

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 useful part (masked top-25 plus the weight/filter definition), but the third sentence repeats that return information already given in sentence one. The definition of Builder rankings in the middle is valuable, yet the surrounding text would tighten to two sentences with no loss.

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 carry the return shape, and it does: masked top-25 rows plus the ranking's weight/filter definition, which is enough to know the payload is both data and configuration. It also explains the domain concept (custom skill leaderboard) needed to interpret that payload. The remaining gap — failure behavior for a bad slug — is minor for a single-parameter read tool.

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?

Only one parameter and schema description coverage is 100%, so the schema fully documents that slug must come from a /r/<slug> share link. The description restates that same fact almost verbatim instead of adding meaning, e.g. slug case sensitivity, whether an unpublished slug is distinguishable from a nonexistent one. 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?

States a specific resource — a published Polyrank Builder ranking — and defines it as a custom skill leaderboard that is a weighting over the metric catalog plus filters, which separates it from the generic leaderboard and rank_wallets siblings. The verb is implicit (the description reads as a noun phrase plus 'Returns...'), so it is a fetch tool by inference rather than by an explicit 'Get...' verb. Still clear enough to identify the tool without opening the 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?

Gives one concrete usage instruction: pass the slug from a shared /r/<slug> link. That is a how-to-invoke rule rather than a when-to-use rule, and it never names an alternative such as polyrank_get_leaderboard or polyrank_list_ranking_templates for the case where the caller has no slug yet. Usage is therefore implied by the 'published / shared' framing but not routed explicitly.

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