resume_search

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the safety profile is covered structurally. The description adds mode semantics but says nothing about the blocking wait behavior, resource cost, or the fact that retrying can append new records to an existing run. It does not contradict the annotations, but it adds only modest context beyond them.

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?

One sentence, front-loaded with the primary action, and each clause corresponds to a genuinely distinct mode of behavior. There is no filler or restatement of the tool name.

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 no explanation, and the three usage modes are covered. What is missing is the blocking/wait semantics and any note that retry operations mutate an existing run's results, which matters for a tool annotated as destructive and non-idempotent.

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 67%: run_id and retry_failed_sources are documented in the schema, and the description's third clause reinforces retry_failed_sources. The undocumented wait_seconds parameter — which blocks up to 240 seconds — is never explained in either place, so the description fails to compensate for the coverage gap.

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 the resource (a search run) and enumerates three distinct operations: checking a running run, retrying a failed run, and retrying failed sources of a completed run. That is specific and actionable. However, it is not fully differentiated from siblings get_run_status and list_runs, which arguably also let an agent 'check' a run, so the boundary is blurry.

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 conditional guidance tied to run state (running vs failed vs completed), which is exactly the context an agent needs to pick this tool. It stops short of naming an alternative such as get_run_status for plain status polling, leaving the routing decision to inference.

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