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

Annotations already establish openWorldHint=true and destructiveHint=false, so safety is covered. The description adds meaningful behavior beyond that: the job is durable and asynchronous (returns a job ID for later status/results) and reusable via the same idempotency_key and body to replay acceptance, which is non-obvious and useful.

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 tight sentences with no filler. The core action and return are front-loaded, and the idempotency replay guidance follows immediately.

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 an output schema exists, return-value detail is unnecessary, and the description correctly focuses on the async job lifecycle and idempotency instead. It is nearly complete, though it could clarify the asynchronous model more explicitly (that results must be fetched via a sibling tool).

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 100%, so all 10 parameters (including the nested limits object and constraints like max_credits, timeout_seconds, browser_renders) are already documented in the schema. The description names the required trio but adds no syntax or format detail beyond what the schema provides; baseline 3 is appropriate.

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 ('Run a bounded durable research job') and names the exact return value ('job ID for status and results'). This clearly distinguishes it from siblings research_status, research_results, and research_search_papers, which operate on an existing job or on standalone paper search.

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 input context ('Provide a query, selected web, paper or developer sources, and a credit budget') so the agent knows what a valid invocation requires. It does not, however, explicitly say when to prefer this over research_search_papers or web_search, nor does it state exclusions.

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