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

Annotations only supply idempotentHint, so the description carries most of the burden and does real work: it discloses partial-update semantics, that null explicitly clears a field, that the call is free, and that submitted cards are immutable. It doesn't cover what a validation failure or the response body looks like, and the partial-update rule sits slightly in tension with a blanket idempotentHint, but there is no 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?

Four very short sentences, front-loaded with the action, each carrying a distinct fact (mutation scope, partial semantics, cost, immutability). No sentence is redundant.

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 mutation tool with no output schema and only an idempotent annotation, this covers the operational essentials: what changes, how to clear, cost, and the state guard. The missing pieces are the return value shape and how validation errors surface, which are minor for a partial-update tool.

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 75% and the schema itself documents most fields, but the key semantic rule — omitted fields are preserved and null clears a field — exists only in the description and is essential to avoid accidental data loss. That is genuine added meaning over the schema, though the 'mistake' parameter is left unexplained in both places.

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?

States a specific verb and resource ('Change a draft postcard') and draws a hard boundary against submitted postcards. It stops short of naming siblings like delete-draft-tool or submit-postcard-tool, but an agent can tell this is the draft-mutation path rather than a create/read/delete tool.

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?

'Submitted postcards cannot be changed' is an explicit when-not condition, and 'Free' tells the agent there is no cost barrier to calling it. There is no routing guidance to delete-draft-tool for removal or submit-postcard-tool to finalize, so the alternatives are implied by siblings rather than stated.

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