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

The description discloses important behaviors beyond the annotations: it fires-and-forgets ('does not wait for the activity to complete'), it 'initiates a multi-step agent process', and it spells out the approval model (manager approval, from-now-on vs just-once, re-ask behavior). These are non-obvious traits that the annotations (readOnlyHint=false, destructiveHint=true) do not convey. No contradiction with 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 core purpose is front-loaded in the first two sentences, and the second block contains essential approval/usage notes. It is slightly dense and contains some internal jargon ('the card is the yes'), but every sentence adds value for correct invocation, so it earns a 4.

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 tool with 5 parameters, no output schema, and a complex approval workflow, the description covers the key contextual gaps: async behavior, approval prerequisites, and when to call. It doesn't describe the return value, but since it says 'returns,' the agent still has some uncertainty. With schema covering parameters, this level of description is adequate but not perfect.

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 every parameter (reason, companyId, agent_name, activity_name, resume_run_id) already has a meaningful description. The tool description adds no parameter-level semantics beyond that, so the baseline 3 is appropriate. The schema does the heavy lifting here.

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 opens with a clear, specific statement: 'Trigger a specific agent to run a specific activity immediately.' It names the exact action and resources, and distinguishes itself from sibling tools like add_agent_activity or update_agent_activity by emphasizing immediate dispatch. The added clarification that it 'does not wait for the activity to complete' further nails the tool's unique role.

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 practical usage context: 'Use this to direct agents to take action' and the sensitive-tier approval note ('Call it on the first clear ask; the card is the yes — do not re-ask in chat.') tells the agent when to invoke it. It does not explicitly name alternative tools or exclusions, so it falls short of a 5, but the guidance is clear enough for a tool with this unique action.

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