Add a word to a banned-words list

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

Annotations already declare readOnly=false, idempotent=true, destructive=false, but the description adds valuable context: the list is checked by audit_text, and the global vs. style-specific scoping with merge behavior is disclosed. This gives the agent a clear model of side effects and scope.

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?

Three sentences, front-loaded with the core function, then expansion on scoping and usage triggers. No redundant words or repetition of schema details.

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 two-parameter tool with no output schema, the description covers the essential behavior (add, check via audit_text), the two modes (global/style), and the usage context. It is complete enough for an agent to select and invoke correctly without further clarification.

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?

Even though schema coverage is 100%, the description adds meaningful semantics to styleId by explaining the global vs. scoped behavior and the merge on top of the global list. Word is self-evident, but the styleId enrichment is significant.

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 clearly states the verb 'Add' and the resource 'banned-words list', and immediately contextualizes it as being 'checked by audit_text'. It distinguishes itself from siblings like remove_banned_word and add_custom_word by specifying the list type and the audit_context.

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?

Provides explicit triggers ('when the user says something like...') and details when to use the global list vs. a style-scoped list via styleId. This goes beyond vague 'use for adding banned words' and gives actionable guidance.

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