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

Annotations already declare readOnlyHint/destructiveHint=false, so safety is covered; the description adds real behavioral context beyond that: newest-first ordering, admin-only access, the before→after payload shape, and cursor-based paging. It stops short of mentioning rate limits or result-size caps beyond the schema's limit.

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?

Three sentences, well front-loaded: identity of the tool and its scope come first, filters second, pagination last. The filter sentence is a long run-on enumeration, but every clause maps to a real parameter, so little is wasted.

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 12-parameter, zero-required read tool with no output schema, the description covers the essential calling decisions: audience/permissions, ordering, filterable dimensions, and pagination. It could be more complete on return record shape and cursor semantics, but nothing critical to invoking it correctly is 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 description coverage is only 25% and 12 parameters exist, so the description does the heavy lifting by mapping filters to parameters: table, record (record_id), person (actor_id), operation (op), source, text search (q) over table/record/field names, time range (from/to), and pagination via next_cursor. This meaningfully compensates for the undocumented schema fields, though it doesn't define allowed source/op values or q syntax.

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 ('who changed what across the workspace') plus the exact record content returned (data changes with before → after values, and account actions like sign-ins). The enumerated scope clearly separates it from siblings such as record_history (single record) and ai_activity_log (AI-only events).

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 parenthetical '(administrators)' signals a permission precondition, and the filter list implies the intended use cases. However, it never states when to prefer this over record_history, activity_summary, or ai_activity_log, which is the key routing decision among the activity-log siblings.

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