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

Annotations declare destructiveHint=true and openWorldHint=true, but the description reads as a benign analytical comparison and says nothing about what is destroyed or charged. The most consequential behaviors — up to a $10,000 maxChargeUsd authorization, mandatory consentExternalProcessing for sending sources to an inference provider, and idempotency semantics — appear nowhere in the description. It is not a direct contradiction, but the framing materially understates the risk profile the annotations advertise.

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?

A single front-loaded sentence with no filler, which is structurally sound. However, concision here shades into under-specification: for a 7-parameter tool with a nested input object and a destructive/billing profile, one sentence is not enough to carry the definition.

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?

The tool is complex — nested inputs, a 75,000-character combined limit, billing authorization, consent, idempotency — and there is no output schema to offload the return-value burden. The description leaves the agent uninformed about cost, consent, side effects, and what the shortlist output looks like, which is inadequate at this complexity level.

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 71%, below the high-coverage threshold, and the description adds no parameter meaning at all. Two parameters, sourceFields and sourceRunIds, are entirely undocumented in both places, so the agent must infer from their names how prior-run context is pulled in and how it interacts with the nested inputs object.

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?

"Compare supplied supplier profiles against your requirements and build a reasoned shortlist" names a specific verb (compare), the two inputs being matched (supplier profiles vs. requirements) and the artifact produced (a shortlist). It is clear what the tool does, but it never distinguishes itself from plausible siblings such as xvendorbench, xscore-bid-evaluation or supplier-risk, so the agent gets no routing signal.

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?

There is no when-to-use guidance, no when-not-to-use, and no named alternative among the many sibling tools. Nothing states the prerequisites that the schema enforces — explicit external-processing consent, an idempotency key, and a payment/charge authorization — so an agent could reasonably attempt a call without understanding the gates.

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