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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and closed-corpus profile is covered structurally. The description reinforces this with 'published Blossom research' (published-only, internal corpus) and the collection-scoping behavior that avoids unrelated hits, but adds nothing about ranking, result volume, or pagination — which is partly offset by the presence of an output schema.

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?

Three short sentences, zero filler, and the corpus scope is front-loaded before the routing advice. Each sentence adds a distinct piece of information: what is searched, how to narrow it, and which alternative tools to prefer.

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?

For a 3-parameter read-only search with rich annotations and an output schema, the definition covers corpus scope, collection narrowing, and alternative-tool routing. The remaining gap is query semantics — what kind of matching `query` performs — which is the one thing an agent could still get wrong.

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 only 33%: `collections` is documented in the schema, while `query` and `limit` carry no descriptive text. The description only partially compensates, explaining that selecting collections avoids unrelated results, but it never clarifies whether `query` is keyword, phrase, or full-text matching, nor how `limit` interacts with the default of 10 and maximum of 20.

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 verb and resource — 'Find published Blossom research across papers, clinical trials, patent families, stakeholder profiles and editorial overviews' — which precisely delimits the corpus. It distinguishes this tool from the per-collection search siblings by pointing to 'native search tools', though it never names them explicitly, so an agent must infer which sibling handles a single-collection query.

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?

It gives clear routing guidance: use this tool with selected collections to narrow results, use 'native search tools' when detailed filters are needed, and use count/aggregate tools for totals or distributions. The guidance is directional but not fully explicit — the sibling tools are described only by category ('native search tools'), so the agent must map that phrase to search_papers/search_trials/etc. itself.

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