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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is covered. The description adds only the kind taxonomy and the pool mapping; it says nothing about whether duplicate names create duplicate stakeholders, whether the addition is reversible, or what the caller needs (existing cap table) beforehand.

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 the action and resource, no filler. The final sentence ("Use only when the user asks") is the weakest and adds little beyond a vague permission gate.

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 tool with no output schema, the description should say what is returned and how ownership/amounts are set later, since the schema exposes only name, kind, email and cap_table. It also leaves the cap-table resolution path (single cap table vs. explicit id) to the schema rather than reinforcing it in prose.

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 50%: email and cap_table already carry good descriptions, and the kind enum is self-explanatory from its values. The description's only real semantic addition is clarifying that kind="pool" denotes an option pool, which is genuinely useful but small.

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 ("Adds a stakeholder ... to a cap table") and enumerates the stakeholder kinds, so the agent knows exactly what entity is created. It does not contrast itself with the closest siblings (add_share_class, record_cap_table_transaction), which is the missing piece for a 5.

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?

Provides one routing rule ("Use kind 'pool' for an option pool") and one vague guardrail ("Use only when the user asks"), but never names alternatives such as add_share_class or record_cap_table_transaction, nor says what to do when a stakeholder already exists. Usage is implied rather than specified.

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