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

Annotations only declare non-readOnly, non-destructive, non-openWorld; the description adds substantive behavior beyond that: board approval and purchaser/company signatures follow, shares and the 83(b) clock start only after verified consideration, and no chat payment assertion can close it. It also discloses idempotency handling and canonicality guidance. The trailing confirmation-boundary sentence is generic boilerplate that lists unrelated operation types, which slightly dilutes the otherwise strong disclosure.

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?

The core is front-loaded and dense, but the definition is one long run-on paragraph mixing domain terms with heavy generic boilerplate (canonicality, idempotency, confirmation-boundary clauses enumerating unrelated action types). The boilerplate costs space without adding tool-specific signal.

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 14-parameter, 12-required mutation tool with no output schema and zero schema descriptions, the description covers the workflow context well: consideration verification, signature/board sequencing, 83(b) timing, and retry/key guidance. The gaps are the undocumented scalar parameters and lack of any return/shape expectation.

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% across 14 parameters, so the description carries the full burden. It does add domain meaning for several inputs (purchaser/officer notice addresses, prior-IP disclosure, vesting start as four-year/one-year cliff, the 83(b) election decision), but it never mentions fairMarketValuePerShare, _corply_context, or the units/constraints for shareCount and pricePerShare, leaving notable gaps.

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 opens with a precise verb+resource+scope: proposing restricted common shares for a new stockholder of a Corply-formed Delaware C corporation, using available authorized shares under a four-year RSPA with a one-year cliff. This is clearly separable from siblings like propose_ip_assignment, propose_cliff_repurchase, and propose_charter_amendment.

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?

It states a concrete prerequisite (authenticated active company access plus all listed conditions) and a confirmation boundary, so an agent knows the entry conditions and that no extra confirmation is needed. It does not, however, explicitly compare against sibling alternatives such as propose_ip_assignment or request_governed_signatures, so routing is only implicit.

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