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

While annotations confirm it is read-only and idempotent, the description adds critical operational context that goes beyond simple hints. It explains the return structure ('actor + entity + action'), the specific fields provided (entityTitle, changedFields), and the pagination logic (reporting 'hasMore' even if the limit isn't reached). This is extremely useful for agent behavior design.

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 detailed, which is necessary for a complex logging tool. It is logically structured, starting with the primary function and scoping, followed by output structure details, and concluding with the usage exception. While comprehensive, its length prevents a perfect 5 for conciseness.

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?

The definition is exceptionally complete. It addresses scope (project, timestamp), limits (100 rows, 30 days), output fields (actor, entity, action, entityTitle, changedFields), and how to handle missing data (null title if deleted). Given the complexity of activity logging, this is comprehensive enough for successful invocation and interpretation.

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 100%, so the baseline is high. The description adds crucial semantic meaning to the output structure, specifically detailing what `entityTitle` represents (the changed entity's current title) and the nature of `changedFields`. This significantly compensates for the structural description, providing deep operational value.

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 explicitly states the tool's function: 'List recent activity... for one project since a given timestamp.' It clearly identifies the resource (ActivityLog) and the necessary constraints (projectId, since). This is highly specific and leaves no ambiguity regarding the tool's core function.

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 a clear exclusion/alternative usage guideline. It specifies a 30-day cap for this tool and directs the agent to use `list_audit_log` for older history, ensuring correct sibling tool selection.

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