Research Web Status

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

The description claims the tool 'Auto-stores completed reports to Weaviate', a persistent state mutation, while the annotations declare readOnlyHint=true (no environment modification). This is a direct conflict, so per the scoring rule it drops to 1 despite otherwise useful disclosure of return 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 short sentences, front-loaded with the primary action and followed by return behavior. No filler, though the auto-store sentence is what creates the annotation conflict and is not qualified.

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 an output schema present, the description need not spell out return values, and it does convey the polling/retrieval semantics. It is nearly complete for a one-parameter status tool, though it omits polling cadence/completion signaling and leaves the store-vs-readOnly conflict unreconciled.

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% and the single parameter's schema text already explains it is the interaction ID returned by research_web. The description adds no further parameter meaning, so the baseline 3 applies.

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+resource (poll/retrieve a Deep Research task) and describes the two outcomes (full report vs. in-progress status). It does not name the sibling research_web that creates the task or distinguish itself from research_web_followup/research_web_cancel, so sibling differentiation is only implicit.

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?

'Poll or retrieve' implies the usage context (checking on a task started by research_web, since the id parameter references it), but there is no explicit when-to-use/when-not statement or routing versus research_web_followup or research_web_cancel. Usage is inferred rather than stated.

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