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

No annotations are provided, so the description carries the full behavioral burden, yet it never states whether the discard is permanent or reversible, whether a discarded draft can be recovered, or whether any permission/state precondition applies. The one useful addition beyond the name is "without sending," which rules out an accidental send but leaves the mutation semantics opaque.

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 core instruction is one efficient sentence, but the definition is padded with a redundant title restatement and HTTP response boilerplate ("**200**: Successful Response", Content-Type) that carries no meaning for an MCP caller. Front-loading is fine; the waste is in the appended transport noise.

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 destructive, single-parameter tool with no annotations and no output schema, the description should at minimum explain the handle and the consequences of discarding. Neither is covered, and nothing indicates what a successful call returns or whether the draft is truly removed.

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%, so the single required parameter "handle" is completely undocumented in both the schema and the description. The description never says the handle identifies the reply draft (vs. a thread, user, or message), nor what form it takes, leaving the agent to guess.

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 sentence "Discard a reply draft without sending" gives a specific verb (discard/skip) and resource (reply draft), and "without sending" clarifies that no message goes out. It falls short of 5 because it doesn't distinguish this from the several near-identical siblings (skip_draft, skip_comment_draft, skip_content_draft), leaving the agent to infer scope from the name alone.

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 statement of when to use this versus the other skip_* siblings or the approve_/rewrite_ variants. The only usable signal — that this discards rather than sends — is embedded in the purpose sentence, not framed as guidance, so the agent gets no explicit selection criteria.

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