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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with "Nothing is read or changed" plus the crucial disclosure that the endpoint is unimplemented and returns nothing. That is real information an agent could not get from the structured fields. One tension: idempotentHint=false is odd for a pure no-op, but it is not a direct contradiction.

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?

The front-loaded statement that documents cannot be generated is good, but the next four sentences circle the same idea ("Nothing is returned in their place", "not yet supported", "Nothing is read or changed") without adding distinct information. It could be one or two sentences.

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 no output schema and no annotations describing the stub behavior, the description correctly carries the critical fact that this tool is a no-op. However, it leaves the five-parameter schema entirely unexplained, which is a meaningful gap for a tool whose signature suggests side effects that the description denies.

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 0% across five parameters, including non-obvious ones like `confirm`, `idempotencyKey`, and `acknowledgedAmountUsd` on a tool that supposedly reads nothing. The description says nothing about what these parameters mean or whether they are ignored, so the agent must guess why a read-only no-op takes an idempotency key and a dollar amount.

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 states a specific resource (tax documents) and, unusually, states the outcome: the server cannot generate them and nothing is returned. An agent immediately learns this tool will not produce data, which is the key fact about its purpose. It gets no credit for sibling differentiation, but the tax-document scope 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?

"This tool is not yet supported" combined with "Nothing is returned in their place" is effectively an explicit do-not-use-for-data directive. What is missing is a stated alternative for obtaining tax documents, so the agent knows what to do instead.

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