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

Goes well beyond the annotations by disclosing the authorization model (agent tokens denied, human owner or admin console required) and the asynchronous start-then-poll pattern. However it omits other behavior an agent needs before invoking: whether the export is billed/rate-limited, how long the job lives, and whether repeated calls create duplicate jobs. With readOnlyHint=false and destructiveHint=false already supplied, this is a moderate addition rather than a full behavioral picture.

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 the core action and the polling instruction, and every clause carries information. The line breaks split related ideas awkwardly (the auth prerequisite is orphaned mid-sentence), mildly hurting scannability, but nothing is padding.

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 6-parameter job-creation tool with an output schema, the description covers the auth gate, follow-up tool, and the most semantically complex parameter, so it is close to sufficient. The opaque include/include_history/include_subtree/scope_ref parameters and the meaning of the enum scope values remain undocumented anywhere, leaving a real gap for a tool with zero schema description coverage.

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 carry the load, and it does explain since_export_id precisely (incremental deltas that, applied after their base, equal a full export) and ties scope to the workspace/namespace key requirement. It leaves include, include_history, include_subtree, and scope_ref entirely unexplained, and does not mention the tenant default for scope.

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 ('Start an export') plus the exact storage format (agentgraph-export/1) and the follow-up tool (get_export), which separates it from list_exports and get_export. It never explicitly contrasts with those siblings, so an agent still has to infer that get_export is the read side of the same job.

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 preconditions (workspace key via workspace or namespace scope, human owner or admin console) and a hard exclusion ('agent tokens are not granted export'), which directly prevents a failed call. It also tells the caller the next step ('poll get_export') and when to use since_export_id for incremental exports.

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