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

Annotations already establish that the tool is read-only, idempotent, and non-destructive. The description adds meaningful behavioral context: results are 'bounded', topic assignments are 'precomputed', filtering is supported, and pagination should continue using 'nextOffset'. 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?

The description is compact and front-loaded with purpose, then filtering capability, then pagination guidance. Each sentence earns its place, though the phrasing is terse and could be slightly clearer.

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 very large nested filter schema and no output schema, the description is incomplete. It does not explain what evidence the response contains, how filters interact, or how pagination with 'nextOffset' maps to the request parameters. An agent would still need significant inference to invoke this tool correctly.

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 carries the burden of explaining parameters. It mentions 'baselReferences' and 'nextOffset', but never explains the top-level parameters (page, offset, pageSize, filters) or their semantics. The large nested filter object is left almost entirely self-describing.

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 ('Read'), a concrete resource ('bounded evidence'), and narrows the scope to 'precomputed editorial, lexical or optional semantic topic assignments.' This distinguishes it from sibling tools like search_works or get_topics_by_period without ambiguity.

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 conveys that this tool reads evidence for topic assignments and supports bibliography filters, so the use case is implied. However, it never explicitly contrasts it with related tools or states when it should be preferred over alternatives.

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