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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), and the description adds substantial context on top: 'hidden' values where the caller cannot see a person or PDF, the visibility rule 'Anybody who sees the project', and the ordering 'Ordered by key'. It omits any hint about result size or pagination, which is the remaining gap.

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 resource is stated first, but the rest is a single tangled sentence with nested parentheticals (e.g. "its authors (the name as the work prints it, and 'personId'/'person'...)") that is hard to scan. The information is useful, but the format costs readability for a three-parameter list tool.

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 burden of describing the returned shape, and it does so field by field (key, authors, title, year, venue, identifiers, pdf, check, dagger). Only pagination/result-size behavior is unaddressed, which for a project-scoped list is a minor omission.

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 baseline is 3, but the description earns more by interpreting the semantics: it spells out what each 'check' value means in domain terms (arXiv/Crossref/zbMATH agreement, 'checkNote', 'checkedBy') and defines 'dagger' as the union of unchecked and mismatch. This gives the agent the notion needed to choose between check values rather than just their names.

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?

It names the resource precisely ('a project's sources — the papers, books and preprints its pages cite') and enumerates the fields returned, so an agent knows exactly what it gets. It does not explicitly contrast with get_source or delete_source, but the plural list semantics are unmistakable.

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?

'Read a work's description here rather than from a page's own list' is an explicit routing instruction against an alternative the agent would otherwise choose. It stops short of naming sibling tools (e.g. get_source for a single work) or stating prerequisites beyond the visibility rule.

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