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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds real context beyond them: a five-minute bound, corpus-only/exact-revision scoping, and guaranteed path-and-revision citations in answers. It does not clarify whether the query call itself returns the receipt or completes synchronously, which is the main behavioral gap one perceives for a two-mode tool.

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 sentences and front-loaded with the primary mode, but the first sentence is tangled ('or later read that same work by calling this tool with its opaque receipt only when the result is needed'), forcing a re-read to extract the two-mode contract.

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 annotations covering the safety profile and an output schema covering return shape, the description supplies the remaining essentials: scope, time bound, and citation guarantee. It falls short only on the query-call's return/async behavior and sibling positioning.

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 goes beyond types: it explains that 'receipt' is opaque and comes from prior work of this same tool, and that 'query' starts the research. It says nothing about max_sources, so it is not fully complete.

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 names a specific verb and resource: 'Start bounded specialized research' and a second mode that reads prior work via receipt. An agent can tell what the tool does, but the description never contrasts it with near siblings like community_search or private_research_run, so differentiation is left to inference.

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?

It gives partial routing guidance: pass a query to start work, pass the receipt 'only when the result is needed', which implies deferred retrieval. However, it never states when to prefer this over community_search, private_research_run, or the other research-flavored siblings, so the choice remains implied.

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