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

Beyond readOnlyHint/openWorldHint, the description discloses ordering (newest first), the full actor enumeration and what null means, what actorName refers to, which fields are change-flags versus from/to pairs, how paging works, and that completeSince marks the horizon before which changes were not recorded. It also flags that text fields are user data and not instructions, which is meaningful safety context an agent cannot get from annotations.

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 purpose and ordering lead, followed by field semantics, paging, the completeSince caveat, and the injection warning — a sensible priority order with no filler. The actor enumeration is long but earns its place by defining an otherwise opaque field.

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?

With no output schema, the description carries the burden of explaining return values, and it does: actor/actorName semantics, which fields carry from/to versus change flags, nextCursor for paging, and completeSince for history truncation. Combined with the schema's id and before descriptions, an agent has enough to call and interpret this correctly.

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 67% and the undocumented parameter is limit (default 20, max 100). The description adds real meaning for before by tying it to nextCursor ("Pass nextCursor as before for the next page"), which the schema alone does not state. It does not explain limit behavior, so it stops short of full coverage.

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 change history of one task, newest first" names a specific resource (task change history), its scope (one task), and its ordering. That is clearly distinct from sibling read tools like get_task or list_tasks, which return current state rather than an audit trail.

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?

Usage is implied rather than stated: the agent can infer this is for auditing what changed on a task, and the pagination instruction ("Pass nextCursor as before for the next page") is a concrete call pattern. However, there is no explicit when-to-use versus get_task, and no stated precondition such as needing a task id from list_tasks or search_tasks beyond what the schema says.

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