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

With no annotations, the description carries the entire behavioral load. It does disclose the sensitive-tier approval gate (first-use vs from-now-on vs just-once), and it implies no other activities or the whole plan are rewritten. But it omits the no-destructive operation details like scheduler re-keying from renaming and the fact that only supplied fields are updated, which a careful caller needs to know.

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 short, front-loaded, and has no filler—an action, a scope, and a safety caveat in three sentences. The most critical information (this edits exactly one activity) is first, and the approval note is placed at the end where it can be processed without cluttering the main purpose.

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 the nested patch object, six top-level parameters, and no output schema, the description is compact but not fully self-contained. It identifies the right use case and the permission gate, but to call it correctly the agent must open the schema to learn the identifier alternatives (agent_id/agent_name, activity_name/activity_index) and the scheduler side-effect; the 100% schema coverage partly compensates.

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 3. The description enumerates some of the available fields (name, description, frequency, tools_used, deliverable, completion_criteria) but adds no new meaning beyond what the input schema already states, and it leaves out the richer sub-properties (priority, workaround, max_iterations, delivery_shape) that only the schema covers.

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 is specific: 'Edit ONE existing activity in a primary activity' — a strong, single-target resource with no ambiguity. It also distinguishes itself from the surgical alternative to regeneration, so the agent knows this is a targeted edit, not a broad plan rewrite, which makes it clear why this tool is different from create/generate siblings.

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?

It explicitly says when to use it: for a surgical single-activity change instead of regenerating the entire plan—a clear context. It does not name the closest sibling tools (e.g., add_agent_activity, remove_agent_activity) or spell out when not to use them, so there is a small but non-critical gap.

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