Delete a blog post. Money is integer minor units (cents). Calling this changes nothing: it returns a preview of what would change and a confirmation link. Only the merchant, on that page, can make it happen.
| Name | Required | Description | Default |
|---|---|---|---|
| post | Yes | The post, by its address under the blog (from blog_posts) or its exact title. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations mark this destructive and non-idempotent, but the description adds genuinely non-obvious behavior: the call itself changes nothing, returns a preview plus a confirmation link, and only the merchant on that page can complete it. That deferred two-step mechanics is exactly the kind of context annotations cannot express. It stops short of stating auth requirements or what the preview contains.
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 delete-and-confirmation sentences are front-loaded and earn their place, but the second sentence about money in minor units is irrelevant copy-paste noise for a tool with no monetary parameter, diluting an otherwise tight description.
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 one-parameter mutation with no output schema, the description covers the important unknown: that the call returns a preview and confirmation link rather than performing deletion. It omits the change-log undo path and the draft alternative, but those are carried by the schema description, so the definition as a whole is close to complete.
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?
With 100% schema coverage on a single parameter, the schema already documents that 'post' is addressed by blog address or exact title. The description adds no parameter meaning at all, and the stray 'Money is integer minor units (cents)' note references a parameter this tool does not even have.
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 opening sentence states a specific verb and resource ('Delete a blog post'), so an agent immediately knows the operation. It does not, however, distinguish itself from nearby siblings such as blog_posts_set_status or blog_posts_edit; that differentiation only appears later in the input schema, not in the description.
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 explains the confirmation flow, which implies when the tool is appropriate, but it never states when to prefer it over alternatives or names a sibling. The only routing hint ('to only hide it, set it to draft instead') lives in the input schema, not the description, so guidance here is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
