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

Annotations declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description earns credit by explaining the source of the non-read-only behavior — the optional indexing retry — and clarifying that the retry does not re-run research. It stops short of describing rate limits, error behavior, or exactly what gets rebuilt.

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?

Two compact sentences, front-loading the read purpose before the retry caveat, with no filler. Every clause carries information.

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 return values need not be described. With only two parameters and the mutation path explained, the description supplies everything an agent needs to invoke it 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 coverage is 50%: retry_index is documented in the schema while run_id is not, and the description adds only that retry is a separate indexing action rather than new research. That partially compensates for the undocumented run_id but adds no format or constraint detail beyond the schema.

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 clear verb (Read) and enumerates the specific resources returned: research progress, category coverage, publication and indexing status. An agent can distinguish it from research_person or cancel_research, though no sibling is named explicitly.

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 second sentence gives guidance for the retry case ('Retry indexing separately without repeating research'), which implies retry_index should only be set when indexing is the problem. However, there is no guidance on when to call research_status versus enrichment_batch_status, submit_enrichment_research, or cancel_research.

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