x_api_activity_stream

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

With no annotations, the description carries the full burden and does well. It discloses read-only risk, bearer token prerequisites, detailed environment-selection behavior (scopeTenantId plus exactly one of scopeUserId/scopeAccountId), credentialKey override, expected response shape, common failure conditions, and safety warnings about sensitive data. This exceeds the structured schema and provides rich operational context.

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 uses labeled sections (Risk, Required permissions, Environment-selection behavior, etc.) which aids scanning. However, the opening 'Activity Stream.' and 'Use when: Activity Stream.' are redundant filler. The rest is informative and not overly verbose, but the tautological parts detract.

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 9-parameter tool with no output schema and no annotations, the description provides valuable context: response shape, failure modes, prerequisites, and an example. Yet it fails to clearly explain what the activity stream represents or what data the agent will receive, and leaves several parameters undocumented. This prevents the description from being fully complete.

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 0%, so the description must compensate. It explains the role of scopeTenantId, scopeUserId/scopeAccountId, and credentialKey in auth resolution, and lists types for backfill_minutes, start_time, and end_time. However, authorizationKey and preferredAuthType are completely unaddressed, and the time parameters lack semantic detail (e.g., format, meaning). Partial compensation with clear gaps.

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 opens with 'Activity Stream.' and 'Use when: Activity Stream.' which merely restates the tool name without a verb or resource. It fails to specify what the tool actually does (e.g., retrieves, lists, streams activity events). This is essentially a tautology and provides no distinguishing information.

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?

'Use when: Activity Stream' offers no actionable guidance. The 'Do not use when' clause mentions preferring x_schema_discovery or x_query_suggestion when exploring, but does not clearly define the positive use case or contrast with similar x_api_* tools. Recommended tools are listed but without explicit when-to-use criteria.

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