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

With no annotations provided, the description carries the burden of behavioral disclosure, and it does well: it reveals hybrid retrieval, filtering of in-flight builds, and explicitly warns that this is not a lookup step. However, 'hybrid retrieval' and the exact shape of the disambiguation response are left unexplained, preventing a perfect score.

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 sentences, no filler, and every sentence carries essential routing information. The core purpose is front-loaded, boundaries come second, and exclusions come last — a model of efficiency.

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 disambiguation tool with no annotations and no output schema, the description covers purpose, scope, filtering behavior, and routing to alternatives. The main gap is the absence of any return-format details, which the lack of an output schema makes more notable.

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 only 33%, so the description must compensate. It reinforces that query is the user's phrasing for a flow name, but it adds nothing about limit or accountId, leaving two of three parameters semantically underdocumented.

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 uses a specific verb, 'disambiguate', names the resource ('FLOW'), and sharply defines its scope ('FLOWS ONLY — never for posts, accounts, links, widgets'). It also distinguishes the tool from get_flow and the bulk tool, so an agent can instantaneously tell what this tool is for.

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 explicitly states when to use the tool ('when several could match') and gives concrete exclusion routing: call get_flow for SEE requests and the bulk tool for CHANGE requests. The description also gestures toward separate tools for non-flow entities, clarifying the boundary further.

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