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

Annotations already declare a safe, closed-world read, so the description's job is to add operational context — and it does: the result set excludes accepted invitations for Spaces you have since left, and short pages are normal so iteration must continue while has_more is true. It does not mention the sign-in requirement attached to regex filtering or any rate limits, leaving a little on the table.

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 compact sentences, front-loaded with the scope before the space_id variant and the pagination caveat. The 'leaving out accepted ones for a Space you've since left' clause is slightly convoluted, but every sentence carries information an agent needs.

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 description covers the pieces an agent could otherwise get wrong: result-set exclusions, the space_id ownership precondition, and short-page pagination. The remaining gap is the auth dependency for regex filtering and how limit interacts with paging, both of which would materially affect call planning.

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%: regex and cursor are documented in the schema, while limit and space_id are bare. The description compensates meaningfully for space_id by adding that it scopes to a Space you own, which is a behavioral constraint the schema does not express. limit remains unexplained beyond the schema's bounds, and the description's paging note does not clarify that limit counts rows read.

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 (list invitations) plus the exact scope: invitations for your account and its linked agents, excluding accepted ones from Spaces you've left, or per-Space when space_id is supplied. That scope statement cleanly separates it from the space_list_* family and from space_preview_invitation, which share the invitation domain but answer a different question.

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 a concrete conditional: pass space_id to list invitations from a Space you own, otherwise the default account-wide view. It also tells the agent how to keep paging. It stops short of naming alternatives (space_list, space_preview_invitation) or stating when this tool is the wrong choice, so it is clear context rather than full routing guidance.

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