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

Annotations cover key behavioral traits: readOnlyHint=false (it mutates), destructiveHint=false (not destructive), idempotentHint=true (safe to retry), and openWorldHint=false (closed enumeration). The description adds the 'privacy-filtered project metadata' context, which is useful. However, the description does not disclose what 'privacy-filtered' means in practice, whether the update is a merge or a replace of existing fields, or what happens when no details are provided.

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?

The description is a single, compact sentence with no filler. It front-loads the verb and resource. It earns a 4 rather than 5 because it omits any detail about parameters or usage guidance, but as concise phrasing it is efficient.

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 output schema and a nested details object, the description is thin. An agent knows it must supply projectId and idempotencyKey (from required fields), but it does not know what 'privacy-filtered' implies, what constitutes a valid activity record, or how the tool relates to the sibling record_agent_execution_activity. Annotations cover idempotency and non-destructiveness, which reduces the burden, but the description alone would not let an agent call this confidently.

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. The phrase 'privacy-filtered project metadata' weakly connects to the projectId parameter, and 'update' maps to the details object (status, summary, referenceIds). Given the complexity of the nested details object and the required idempotencyKey, a brief note about the purpose of the idempotencyKey or the three detail subfields would strengthen it. Still, the description plus schema gives an agent enough hint of intent for most parameters.

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 says 'Update hosted record activity using privacy-filtered project metadata,' which specifies a verb ('update'), a resource ('hosted record activity'), and a qualifier ('using privacy-filtered project metadata'). However, this is vague: it does not explain what 'record activity' means, what kind of update is performed, or how this differs from siblings like 'record_agent_execution_activity' or 'activity_write,' both of which appear plausibly related.

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?

The description provides no guidance on when to use this tool versus alternatives. The phrase 'privacy-filtered project metadata' hints at a privacy-related context, but there is no explicit statement of when to choose this over record_agent_execution_activity, activity_write, or context_write. The sibling list is large (140+ tools), and without routing guidance an agent cannot reliably distinguish this from similar record/activity tools.

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