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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds context the annotations cannot: the no-modes call writes nothing and merely returns a proposed binding, while the modes call persists what is confirmed, plus the vendor-key prerequisite. It does not state what happens when the same ref is added twice, which matters given idempotentHint=false.

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?

Two dense sentences that front-load the core action and then split cleanly into the two modes. The phrase 'each { endpoint, slot, binding } built from that proposal' is slightly compressed and takes a second read, but no sentence is filler.

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 five-parameter tool with deep nesting and an output schema, the description covers the action, the two invocation branches, the write semantics of each branch, and the precondition. Return values are handled by the output schema, so remaining omissions (kind, label) are minor.

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 20% and the description compensates well for the hardest parameter, spelling out the { endpoint, slot, binding } shape and the binding's prompt_field/media_fields/output components. It says nothing about 'kind', 'label', the 'controls' array, or how 'ref' should be formed, so a quarter of the surface is still undocumented outside the schema.

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 and resource ('Add a vendor model to the account's own key') and clarifies that the tool has a preview branch and a save branch. It never names its nearest siblings (update_own_model, list_own_models, generate_with_own_model), so an agent must infer the boundary from the name alone, but the tool's own function is unambiguous.

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 explicit branch selection: omit 'modes' to probe the vendor and get a proposal without saving, supply 'modes' to persist confirmed endpoints and bindings. It also states a hard prerequisite — the account must hold a key for the vendor. What's missing is guidance on when to prefer this over update_own_model for a model already registered.

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