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

With annotations only covering openWorldHint=false and destructiveHint=false, the description adds real behavioral context: existing people are matched by id and only stated fields change (merge/upsert semantics), and failed invitations are reported but never block the filing (non-atomic error handling). These are valuable disclosures beyond the annotations, though auth requirements and rate limits remain unaddressed.

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?

Four tight sentences, front-loaded with purpose followed by validation, merge semantics, and error handling. No filler. Minor opportunity to make the alternative-tool relationship known, but the structure is efficient.

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 values need not be explained. For a complex nested mutation the description covers validation, partial-update semantics, and failure handling well. The gap is election83bIntent, which is a required-to-understand behavior flag (83(b) election intent) left undefined for an agent operating on a formation.

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 only 25%, so the description must carry more weight. It does explain the ownership-total constraint, id-based matching for members, vesting, and the invite/failure behavior, which maps to several parameters. However, election83bIntent is never mentioned and role/title/dateOfBirth semantics are left entirely to the schema.

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: 'Sets the founding team's ownership split and vesting.' The 'team' framing implies a bulk operation distinct from the single-shareholder siblings (formation_add_shareholder, formation_update_shareholder), though it never names them explicitly. An agent can infer the purpose clearly, but the sibling differentiation is left implicit.

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?

The description states constraints ('Ownership must total exactly 100%') but gives no guidance on when to choose this over formation_add_shareholder, formation_update_shareholder, or the cap_table_* tools. There is no explicit when-to-use, when-not, or named alternative anywhere in the text.

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