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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description reinforces and extends them rather than repeating: 'Preview writes/sends nothing', execution only via the human approval card, per-change-type permission requirements, stale-card/no-retry handling, and the secret-hygiene rule 'Never expose hidden tokens or login links.' That is substantive behavior an agent could not get from the annotations alone.

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?

Very dense and free of filler, but written as clipped imperative fragments rather than a front-loaded statement of what the tool does; the purpose only emerges from the third clause. Safety and secret-hygiene rules are appended at the end rather than grouped, making it harder to scan.

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 two-parameter preview tool with no output schema, the definition covers the critical path: where expectedRevision comes from, what gets validated (recipient, role, native rules, last-active-owner protection), who can execute, needed scopes, and stale-card behavior. It is less complete about what the call returns (an approval card id? a preview object?) and about when to choose prepare_team_invitation instead.

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 0%, so the description must compensate, and it does meaningfully: expectedRevision must be copied exactly from get_team_access (a concurrency token, not user-supplied), membership identity comes from 'existing membership/invite identity or newInviteId', and recipient/role must match exactly. It still does not explain the four change variants or the role enum values, leaving part of the `change` union semantics to the schema alone.

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?

The description makes clear this is a non-executing preparation step for a team membership/role/invite change: it says to read get_team_access first, copy the exact expectedRevision, and that 'Only the human show_team_approval card can execute.' It never states the purpose in one plain sentence (the opening clause is procedural), but the verb+resource and the split from get_team_access (read) and show_team_approval (execute) are inferable.

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 real precondition ('After explicit request'), maps change types to required scopes ('Invite needs team:invite; role/access/revoke need team:write'), and routes the execution step to show_team_approval and the data source to get_team_access. It also handles the edge case of expired/stale cards ('require read without retry'). It stops short of explicit when-not-to-use guidance, and does not address the overlapping prepare_team_invitation sibling.

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