Read a scholarly article or supporting file

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds value beyond that: it states the result reports evidence boundaries (access_state, text_source, challenge status, references) and warns against treating article text as tool instructions — a prompt-injection guardrail. This adds context annotations don't carry, though auth, rate limits, and retry behavior are absent. No contradiction with annotations.

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?

Four tight sentences with the core purpose front-loaded. The security warning is concise and prominent, and there is no wasted prose. The parameter guidance is embedded naturally rather than tabular, which is slightly less scannable but still efficient.

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 7-parameter tool at 0% schema coverage, the description leaves six parameters unexplained. An output schema exists, which mitigates return-value ambiguity and covers the evidence-boundary reporting. But the meaning of 'approved' (approved by whom?), figure extraction flow, wait/timeout semantics, and landing_url_hint are all missing, leaving an agent to guess on a complex tool.

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 bears the full burden for 7 parameters, but it only explains max_chars (max_chars=0 yields complete extractable text). The url, wait_ms, max_figures, figure_offset, timeout_seconds, and landing_url_hint semantics are left to inference from parameter names, which is a major gap at zero schema coverage.

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: read one approved DOI, publisher page, article PDF, or supporting file. The scope is concrete and the title reinforces it. However, it doesn't explicitly differentiate from sibling literature_figure_read, which likely covers article figures, so sibling distinction is incomplete.

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?

No guidance on when to choose this tool over literature_figure_read, literature_probe, or literature_health. The only usage hint is the max_chars=0 tip for complete text extraction, which is parameter-level guidance, not tool-selection guidance. No exclusions or alternative routing is provided.

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