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

Annotations already carry readOnly=false, idempotentHint=true, and destructiveHint=true, so the bar for additional disclosure is lower. The description adds non-obvious behavioral constraints: supplier proof must come from reusable company context, never the buyer clause or an old offer, and the result is a proposal rather than an approval. No contradiction with the annotations is present.

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, each earning its place: the primary action, the required content categories, and the boundary of what the tool cannot do. It is front-loaded and free of fluff, though the middle sentence packs several field concepts into a somewhat dense list.

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 complex tool with nested objects, five required parameters, no output schema, and an idempotent destructive mutation, the description gives solid domain rules but omits key operational guidance: how analysisRevision/expectedRevision relate to the 'exact current analysis', what happens on revision mismatch, and expected return behavior. Annotations and the idempotencyKey schema description cover some gaps, but not all.

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 only 40%, so the description must compensate. It does meaningfully map to nested qualification fields: mandatory conditions with 'unknown stays unknown', sourced deadlines, missing annexes, strategy, and proposed blocks. However, it does not explain the technical revision parameters (analysisRevision, expectedRevision), which remain opaque even though the tool depends on them.

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 opens with a specific verb and resource: 'Save your sourced qualification against the exact current analysis.' It also distinguishes itself from approval-type tools by explicitly stating 'This is a proposal and cannot approve a bid or production,' making its purpose unmistakable against the large sibling list.

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?

The description implies when to use the tool (when you have a sourced qualification to persist against the current analysis) and gives a clear when-not ('cannot approve a bid or production'), but it never names alternative tools such as helvabase_read_qualification or helvabase_confirm_bid_decision. The usage context is clear, yet alternative routing is left to inference.

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