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

Annotations already cover read-only, open-world, idempotency and destructiveness, so the description's extra value is cost and timing: it discloses credit pricing per effort tier and that charges only apply when the report is written. It also flags the async behavior and the returned identifier, though nothing is said about duration or failure/cancellation behavior.

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?

Three compact clauses with zero filler: what it does, how to retrieve the result, and what it costs. The action and the next step are both front-loaded.

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 two-parameter, no-output-schema tool, the description supplies everything needed to invoke it correctly and to continue the workflow via research_result. The cost-per-tier detail closes the only real gap left by the schema.

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% with 'input' documented in the schema and 'effort' left as a bare enum. The description compensates by mapping lite/standard/deep to concrete credit costs (30/75/200), which gives the agent real decision-relevant meaning for the undocumented parameter.

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 ('Start an async deep-research task') and enumerates what the task actually does: planned web searches, page reading, and a cited Markdown report written by Claude. That detail clearly separates it from siblings like search, answer, or crawl.

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?

Explicitly says it returns a task id and to 'call research_result with it', which is a clear follow-up path. It does not explicitly state when to prefer this over the 'answer' sibling or quick search, but the 'deep-research task' framing implies the heavy-weight case.

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