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

With no annotations, the description carries the full burden and does so well: it discloses versioning, sha256 digest, a signed receipt, and the significant consequence that every other member must accept before reading or posting again. It also documents required auth (OAuth connector sign-in or agent API key in the Authorization: Bearer header) and the constraint never to pass keys as arguments.

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?

Front-loads the permission gate and the core action, then layers versioning, member-acceptance, room semantics, and auth in tight sentences. Slightly dense, and the auth/key sentence is long, but virtually every clause carries operational information.

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 annotations and no output schema, the description covers side effects (other members locked out until acceptance), versioning artifacts (digest, receipt), scope layering, and authentication. The main remaining gap is failure behavior when the caller is not the lead, and the workspaceName parameter's exact meaning.

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%: the schema describes text and space, but template (enum, no description) and workspaceName (no description) are bare. The description recovers template by explaining '"default" for the default charter' and hints at workspace scope via the private-room/workspace-charter sentence, but workspaceName's role and format are never explained, so compensation is only partial.

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+resource (set the space's charter) and immediately scopes it as 'Lead only', which distinguishes it from siblings read_space_charter and accept_space_charter. It also clarifies that the charter is 'rules, free text you write', removing ambiguity about what a charter actually is.

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 clear precondition ('Lead only') and an explicit alternative mode ('or template "default" for the default charter'), plus context on when this is a room-rules override ('in a private room this sets room rules on top of the workspace charter'). It does not name sibling tools (e.g. use read_space_charter to view, accept_space_charter to accept), so routing is inferred rather than stated.

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