Pubmed Fetch Fulltext

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

The description discloses fallback logic, source transitions (PMC → Europe PMC → Unpaywall), and data formats (structured JATS). It explains dependencies like UNPAYWALL_EMAIL and covers parameter-specific behaviors. Annotations (readOnlyHint, openWorldHint) are consistent and not contradicted.

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?

The description is a single paragraph that front-loads the main purpose, then details fallback and input requirements. It is succinct without redundancy, though could be slightly more structured with bullet points. Every sentence serves a purpose.

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?

Given the output schema exists and complexity of the tool (multiple input types, fallbacks, filters), the description is thorough. It covers all parameters, explains resolution logic, and sets expectations for output structure. No critical gaps identified.

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%, providing baseline 3. The description adds value by explaining the resolution logic for each input type and fallback behaviors, as well as constraints like pmcid pattern. It also clarifies parameter applicability (e.g., includeReferences applies to pmc results only).

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 clearly states the tool fetches full-text articles from PubMed Central with structured sections and references, specifying the resource and action. It distinguishes from siblings by detailing fallback to Europe PMC and Unpaywall, and explicitly lists input methods (pmcids, pmids, dois) with auto-resolution behavior.

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?

The description provides explicit usage guidance: 'Provide exactly one of pmcids, pmids, or dois' and explains fallback behavior. It mentions conditional behavior (Unpaywall fallback when email is set) but does not explicitly contrast with sibling tools like pubmed_fetch_articles for abstract-only use.

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