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

Goes well past the readOnly/openWorld annotations: it discloses the default-resolution rule by auth state, that the result may be partial (not_searched), that an empty private list does not prove access in another host so the account must be verified, and that listing has no side effect on Personal Space creation. These are exactly the auth and partial-result behaviors an agent cannot infer from annotations.

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-loaded with purpose and scope before the edge cases, and every sentence carries a distinct rule (defaults, not_searched, sign-in, pagination, empty-list caveat). The phrasing 'Use spaces[].space_id as space_id' is terse to the point of ambiguity, which costs a point.

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?

With an output schema present, the description needn't explain return shapes, and it correctly focuses on what the schema cannot convey: auth-dependent defaults, partial results, and the no-implicit-Personal-Space guarantee. Nothing an agent needs to invoke this correctly appears to be missing.

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 75%, so the schema already carries most parameter detail, but the description adds real meaning for scope (defaulting and the sign-in failure mode) and for pagination (continue while has_more is true, use spaces[].space_id as space_id). limit is left to the schema's regex note about 'limit counts rows read,' which is a minor residual gap.

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?

Opens with a specific verb+resource ('List Spaces') and immediately scopes it into two variants: private spaces and Community Spaces. An agent can tell this is an enumeration tool rather than a lookup or search, though no sibling (e.g. space_search, space_get) is named to sharpen the boundary.

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 explicit selection logic: omit scope for the default side, 'send scope to list that side' to get the other, and warns that 'scope: private with no account asks for sign-in.' It also explains that not_searched names the side that was skipped, so the agent knows how to recover. It stops short of naming a specific alternative tool for cross-space lookup.

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