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

Annotations already declare readOnly, idempotent, closed-world, non-destructive behavior, so the safety profile is covered. The description adds genuinely non-obvious behavior: labels are sanitized (input may be altered in the output) and dangling edges are rejected (hard validation failure rather than silent dropping). It does not mention the node/edge count caps (40/80) that will also cause failures.

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?

Two short sentences, zero filler, with the core action front-loaded before the behavioral caveats. Nothing here could be cut without losing information.

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?

An output schema exists, so return-value explanation is unnecessary, and annotations cover the safety profile. Still missing for a structured-input builder: the cardinality limits, the id format constraint, and what 'sanitizes labels' actually does to a label (strip characters? truncate?). An agent can probably call it correctly but may hit avoidable validation errors.

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 description must carry parameter meaning, and it does partially: it frames the two parameters as nodes and edges and conveys that edge endpoints must reference existing nodes ('rejects dangling edges') and that labels are sanitized. However, it says nothing about the node id pattern (^[a-zA-Z][a-zA-Z0-9_]{0,39}$), the 40-node/80-edge maximums, or that edge labels are optional and length-capped.

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 names a specific verb and resource ('Build Mermaid from explicit nodes and edges'), so the agent immediately knows this produces a diagram artifact from a node/edge graph rather than prose or a pattern recommendation. It implicitly distinguishes itself from sequence_diagram and c4_model by requiring an explicit graph input, but never names those siblings to make the contrast 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?

There is no statement of when to reach for this tool versus sequence_diagram, c4_model, or architecture_pattern, all of which are plausibly adjacent in the sibling list. The only guidance is an input-shape precondition ('from explicit nodes and edges'), which tells the agent what to supply, not when to select this tool.

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