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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is the access-control behavior: a stakeholder-only user sees only their own holding. It also discloses that ledger ids are what you need to void a transaction, linking this read to a sibling mutation. It stops short of noting pagination or how omitted as_of defaults.

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?

Front-loaded with the verb and the as-of scoping, followed by a compact content enumeration and one permission caveat. The middle sentence is dense with semicolons but every clause names a distinct returned entity, so there is little waste; a bulleted content list would read marginally faster.

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?

With no output schema, the description carries the burden of describing return values and does so concretely (holdings, classes and preferences, SAFEs, notes, rounds, optional ledger). Combined with the annotations and fully described parameters, an agent has everything needed to call it correctly.

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 100% and every parameter already carries a description, including the cap_table omission rule and the ledger/void rationale, so baseline is 3. The prose only restates as_of and include_ledger at a high level rather than adding format or edge-case detail the schema lacks.

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 ("Returns a cap table as of a date") and immediately enumerates the payload: per-stakeholder shares by class, options and vested options, pool, fully diluted counts, classes with preferences, SAFEs, notes, rounds. This clearly distinguishes it from list_cap_tables (enumeration only) and calculate_exit_waterfall (simulation).

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 implies usage through the as-of framing and the optional ledger, but never says when to call this instead of list_cap_tables, get_company_valuation, or calculate_exit_waterfall. There is no explicit when-not guidance and no prerequisites stated beyond the stakeholder-visibility note.

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