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

Annotations only declare write/openWorld/non-destructive; the description adds substantive behavior the annotations do not: affected founders are notified, payment and filing are held pending the incorporator's decision, and requestId must be generated once and reused on retry. The canonicality/idempotency/confirmation paragraphs are useful but partly generic boilerplate.

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?

Purpose and key behavior are front-loaded, but roughly half the text is reusable boilerplate (Canonicality, Idempotency, Confirmation boundary) that reads as template padding rather than tool-specific guidance.

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 mutation with no output schema, 5 parameters and a nested _corply_context object, the description covers workflow, recipients, hold behavior and retry semantics well. The remaining gap is the unexplained message/formationId parameters.

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 0%, so the description must carry the parameter burden. It meaningfully explains requestId (generate once, reuse on retry) and ties revisionId to the 'exact current revision', but message and formationId are never described, leaving two required parameters undocumented.

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 specific verb and resource: a founder 'proposes a change to the exact current revision', and clarifies this is not an edit or a signature. It implicitly differentiates from the sibling decide_formation_change by noting payment/filing is held until the incorporator decides, though it never names that sibling.

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 context (founder-initiated, prerequisite of authenticated active company access, confirm with the founder before sending) and an implicit alternative ('instead of editing or signing it'). It stops short of explicitly naming which sibling tool to use when a revision should be edited, signed, or decided instead.

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