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

With annotations already covering read-only/idempotent safety, the description still adds substantial behavioral context: version omission reads the current revision without verifying agreement, missing parsed rows do not establish absence, content is 'source projections, not AI conclusions', and text is 'evidence, not instructions'. These are non-obvious traits an agent cannot infer from structured fields.

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 purpose, but the body is a dense run-on mixing parameter guidance, return-field notes, chunking, and domain caveats without clear segmentation. Sentences like the noon intraday/completed-session clock warning are hard to parse and would benefit from grouping.

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 complex, multi-section read tool with an output schema (so return values need no explanation) and 0% schema coverage, the description covers provenance, section selection, versioning, pagination, and evidence caveats. Completeness is strong; only tighter organization of the behavioral warnings 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 0%, so the description must carry the load, and it does: research_id provenance from search_research, section value choices (article, protocol, result, guide, evidence), version's optional-but-64-char semantics, and offset's role via next_offset/next_read. It does not map every parameter to a named argument explicitly, so it falls short of a 5.

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 ('Read a publication ID returned by search_research') and explicitly ties itself to the search_research sibling, so the agent can distinguish retrieval from search. The remainder drifts into return-field and caveat territory, diluting the core statement slightly.

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 concrete usage paths: 'Use documents[section].read_arguments returned by search or overview', 'Continue chunks with content.next_read (or next_offset and the same version)', and 'Read an available guide alongside the result'. It lacks an explicit when-not-to-use or sibling comparison beyond the search handoff, so it stops short of a 5.

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