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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower. The description adds real behavioral context beyond the schema: markdown rendering with paragraph/line-break preservation, the exactly-one-target constraint, and the semantic meaning of ai_generated for human-vs-AI attribution.

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 tight sentences, front-loaded with the core action, then rendering behavior, then the identifier constraint and the ai_generated rule. Each sentence earns its place; the closing clause on visual distinction is slightly wordy but still informative.

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?

No output schema exists, so return values need not be described, and the description covers the target selection rule, body formatting, and the attribution flag. It leaves out edge-case behavior (e.g., supplying both company and person) and any permission/rate context, so it is complete but not exhaustive for a 4-parameter mutation tool.

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 already 100%, so baseline is 3, but the description adds meaning the schema lacks: the one-of constraint on company vs person (the schema marks neither as required and has no oneOf), the slug-vs-uuid provenance, and the default/attribution intent of ai_generated. This meaningfully exceeds what the structured fields convey.

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?

States a concrete verb+resource ('Add a note') and names the three valid target entity types (company, pitch, person), which is more specific than most siblings. It does not explicitly contrast with sibling tools like create_transaction or update_company, so it stops short of full sibling differentiation.

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?

Gives clear operational context: exactly one of company/person must be supplied, and it points to the tools that yield valid identifiers (list_companies/list_pitches for slugs, list_people for uuids). It also says when to set ai_generated. No explicit when-not-to-use or alternative-tool routing, so it is clear context without full exclusion guidance.

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