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

Goes well beyond the readOnly/idempotent/non-destructive annotations: it discloses the auth requirement and scope, that nothing is persisted ('Files nothing'), that no model is called, and that rendering only happens in MCP Apps hosts. That host-dependent behavior is exactly the kind of trait annotations cannot express.

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?

Front-loaded with the hard prerequisite, then the operation, then the per-block output, then the negative side effects and the sibling handoff, so no sentence is filler. It is dense and parenthetical-heavy, and the enumerated outcome clause runs long, which costs a point on readability rather than on waste.

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?

Given an output schema, the return shape need not be spelled out, yet the description still characterizes what comes back per block. Combined with auth, side-effect and host-rendering disclosure, an agent has everything needed to decide whether and how to call it.

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 100% and the single parameter's description already states both accepted modes (whole post including frontmatter, or one mermaid source) and the 200,000-character cap. The description restates the dual-mode input but adds no format or syntax guidance beyond the schema, so the baseline 3 applies.

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?

Specific verb+resource: it reads every ```mermaid block in a post (or a single mermaid source) and reports lines, caption, parse status with error location, and rule findings. It names the sibling it is not (lint_draft) and the drafting stage it belongs to, so an agent can separate it from lint_draft without opening either schema.

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?

Explicit timing and alternative: 'use it while drafting, then lint_draft the whole post' tells the agent when to reach for this tool and what to do next instead of relying on it for whole-post checks. The precondition (engineer sign-in, blog.write scope) is stated up front rather than discovered at call time.

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