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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value on top: it discloses the depth of retrieval (whole text including every section and figure caption) and the output format (Markdown), plus the open-access scope constraint. It stops short of saying what happens on a missing or closed-access record, or whether long articles are truncated.

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?

One sentence, front-loaded with verb, source and identifier, then a compact enumeration of the payload. Nothing is redundant and nothing padding-like; the list of returned fields is doing descriptive work rather than filler.

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 enumerating return fields is largely optional, and the openWorldHint plus readOnlyHint cover the network/safety picture. What is missing is treatment of the awkward nested `_subject`/`_files` parameters and the closed-access failure case — the two things an agent could actually get wrong when calling this.

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 100%, so the schema already documents `id` with concrete PMCID/PMID examples; the description merely restates the same identifier forms. The nested `_subject` and `_files` parameters carry dense, seemingly unrelated record-template descriptions that the tool description does not reconcile with an article fetch, leaving a real ambiguity untouched. 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 verb and resource ('Fetch a paper's whole open-access text from Europe PMC'), names the accepted identifier types (PMCID or PMID), and enumerates what is retrieved. It is clearly distinguishable from lookup-style siblings, though it never names the sibling (e.g. search_literature) an agent would use to obtain a PMCID in the first place.

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?

Usage is only implied: the agent can infer this tool is for when it already has a PMCID/PMID, and the word 'open-access' faintly signals the paywalled case will not work. There is no explicit when-to-use statement, no pointer to search_literature for finding an ID, and no stated behavior for non-open-access papers.

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