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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds real behavioral value beyond that: it discloses the cardinality bound (2–4), the fact that one filter set is applied uniformly across all cohorts, the output dimensions reported, and that overlapping collections are allowed rather than deduplicated.

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?

Two compact sentences, front-loaded with the action and cardinality, followed by output expectations and a single caveat. No filler or restatement of the tool name.

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?

An output schema exists, so return values need not be explained, and the description's summary of reported metrics is a helpful supplement rather than a requirement. Combined with annotation coverage of the read-only profile, an agent has enough to call this correctly; only per-filter semantics remain thin due to the 0% schema coverage.

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 0%, so the description carries the full burden. It usefully clarifies that `filters` is shared/identical across all `cohorts` and that `cohorts` accepts projects or item sets sized 2–4, but the roughly twenty filter fields (genre, country, year_from/to, has_media, etc.) receive no explanation, so compensation for the coverage gap is only partial.

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 ('Compare 2–4 projects or item sets') and immediately scopes the operation to a comparison across cohorts. This clearly distinguishes it from the sibling list_/get_/search_ tools, which retrieve a single entity or a flat result set. It also previews the output dimensions (denominators, missingness, dates, top types/languages).

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?

'Compare 2–4 projects or item sets with identical research-item filters' gives a clear condition for use: multi-cohort comparison under one filter set. The caveat 'collections can overlap' warns about a likely misuse assumption (that cohorts are disjoint). However, no sibling alternative is named for the single-collection case (e.g., get_collection_overview or list_collections), so routing guidance is implicit.

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