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

Annotations already declare destructiveHint=true and openWorldHint=false, so the safety profile is partly covered. The description adds real context beyond them: the grant is time-bounded and the investor is told their reads are visible — a non-obvious side effect. It never explains what the destructive flag means here (i.e., that this widens access) or what happens at expiry.

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?

Two tight sentences with the action and its scoping constraint front-loaded and no filler. The phrase "tell them their reads are visible" is slightly ambiguous in wording but still earns its place by flagging a disclosure side effect.

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 no explanation, and the required-parameter story is partly told. Still, for a destructive, nested-object mutation with only 25% schema coverage, the description leaves the recipient-identity mechanics and expiry behavior unexplained — an agent could plausibly call it with mismatched email/confirmRecipient values.

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 weight; it partially does — "with an expiry" maps to expiresAt and "confirm by naming the recipient address exactly" gives the only real guidance on confirmRecipient, which the schema leaves undocumented. It never addresses why both email and relationshipId exist or how the address to confirm relates to them.

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 — opening data room access to exactly one investor with a time bound — which distinguishes it from read-oriented siblings like fundraising_get_data_room and fundraising_get_list_data_room_grants. It never names the inverse sibling fundraising_revoke_data_room_access, so the differentiation is inferred rather than stated.

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?

"Open the data room to one investor, with an expiry" implies the granting scenario and the singular-recipient constraint, but no explicit when-to-use/when-not guidance or pointer to the revoke counterpart. The closing sentence is a parameter instruction rather than a usage guideline.

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