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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the mutating/world-touching profile is covered. The description usefully adds that this is a follow-up into a live run and that answering a pendingQuestion requires a specific field combination, but it never says whether sending a message resumes execution, blocks, costs tokens, or what comes back.

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 short sentences, front-loaded with the core action, then the reply recipe, then the exclusion. No filler or restated title text.

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 6-parameter write tool with a nested `data` object and no output schema, the description only covers the question-answering path. Nothing tells the agent how content relates to action/data in the general follow-up case or what happens on a completed run, leaving real gaps for correct invocation.

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 0% across 6 parameters, so the description must carry the load, yet it explains only sourceMessageId, action and data, and only within the pendingQuestion path. The two required parameters runId and content, plus idempotencyKey, get no semantic explanation, and the content-vs-action-vs-data split is left ambiguous.

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?

Specific verb plus resource ('Send a follow-up in an existing agent run') and an explicit negative scope that separates it from agent_run_start: 'Do not use this tool to start new work.' An agent can distinguish this from its siblings without opening any schema.

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?

Gives a concrete use case tied to another tool ('To answer pendingQuestion from agent_run_get') and states an exclusion ('not to start new work'). It stops short of naming agent_run_start as the alternative and says nothing about when idempotencyKey should be supplied.

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