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

Annotations already declare this a read-only, idempotent, non-destructive, open-world operation, and the description adds substantial extra context beyond that: pagination size (10/page), that total count and page count are returned, the underlying data source (PubTator 3 index at NCBI/NLM, ~36M abstracts + PMC OA full text), and that it is keyless (no auth). That is exactly the behavioral detail annotations cannot convey.

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 core action and return value, then progressively adds query forms and provenance. The single dense sentence with parenthetical enumerations is information-rich and mostly earns its length, though the run-on structure and repeated example syntaxes make it slightly heavier than necessary.

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 return-value burden and does so: matched sentence per paper, decoded/normalized entity mentions across six biotypes, result count, and page count. For a two-parameter read-only search tool, nothing an agent needs to invoke it correctly is missing.

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 coverage is 100%, so the baseline is 3, and the description exceeds it by spelling out the query string grammar (free text, @ENTITY_id joined with AND/OR, and the relations:<type>|entity1|entity2 form) plus how to source ids. The page parameter's 1-based, 10-per-page semantics are reinforced rather than newly explained.

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 (Search) plus resource (PubMed/PMC literature) and precisely what is returned: the matched sentence per paper with entity mentions decoded and normalized to ids. This scope cleanly separates it from siblings like pubtator_annotations (annotate a document) and pubtator_find_entity (resolve an entity name to an id).

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 clear usage context by enumerating the three accepted query forms (plain text, entity-id boolean, relation query) with concrete examples, and routes to pubtator_find_entity for obtaining ids. It does not, however, state when to prefer this over pubtator_relations or pubtator_annotations, so it stops short of explicit alternatives/when-not guidance.

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