agent_activity_query

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: default COMPACT projection is trimmed (NOT missing fields), the I/O summary is excerpted due to result ceiling, windows capped at 50 rows, and sorted by timestamp descending. It adds material behavioral context beyond what the schema conveys.

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 tightly crafted, front-loaded with purpose in the first line, then organized into a compact logical flow: what's returned, default projection behavior, why (with measured evidence), and how to adjust. Every sentence earns its place; no filler or redundancy.

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?

Given an output schema exists (so return values are documented there), 4 params all with 100% schema coverage, and the description thoroughly explains the projection behavior, row caps, sorting, and the tuning strategy, the description is fully complete for an agent to select and invoke this tool appropriately.

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 100%, so baseline is 3. The description adds value by clarifying the relationship between fields='compact'/'all' and the excerpt semantics, explaining that the compact window caps at 50 rows while the limit parameter defaults to 20, and noting agent_id narrows rather than widens. The interplay between limit and window cap is genuinely useful beyond schema alone.

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 clearly states it 'Query Agent activity records for a team', specifying the verb (Query), resource (Agent activity records), and scope (for a team). It distinctively reports tool name, duration_ms, and I/O summary, differentiating it from siblings like task_run, agent_list, or meeting tools. Well-defined purpose.

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 explicitly documents the default compact projection, explains the reason (43.9k char transcript ceiling), and provides concrete guidance: narrow with agent_id rather than widening limit for narrower windows, and use fields='all' for full records. It tells the agent exactly when and how to adjust parameters for different needs.

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