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

Annotations already flag destructiveHint=true and non-idempotency, so the safety profile is covered. The description adds genuinely new behavior: the void is a soft delete that preserves history, and the call will be refused when later transactions depend on it — a failure mode the annotations cannot express. It does not say whether voids can be reversed or what the response contains, but the key operational risks are disclosed.

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 short sentences, front-loaded with what the tool does and its history-preserving effect, followed by the refusal rule and the usage guardrail. No filler or redundant restatement of the name.

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 destructive single-record mutation with annotations covering safety and no output schema, the description supplies the essential context: soft-delete semantics, dependency-based refusal, and the id source. The only meaningful gap is the undocumented 'reason' parameter.

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 only 33%: cap_table is documented in the schema, while transaction_id and reason are not. The description partially compensates by pointing to get_cap_table with include_ledger as the source of the transaction id, but the optional 'reason' parameter is never explained anywhere.

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 ('Voids a transaction') plus the crucial semantic consequence ('it stays in the history, marked void'). This is clearly distinct from siblings like record_cap_table_transaction and get_cap_table, which are the only adjacent operations.

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 an explicit guardrail ('Use only when the user asks') and tells the agent where the required id comes from ('get_cap_table with include_ledger'). The refusal condition for dependent transactions is also a use-time consideration, though no alternative action (e.g., recording a reversing entry) is suggested.

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