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

With no annotations, the description must carry the behavioral burden. It discloses that the operation is non-destructive (only drafts), that it appends an event named 'standing.drafted', and that the live state is read via process_run_get. This is transparent about the effect. It does not mention permissions or rate limits, but those are not critical for typical use; the core behavior is well-covered.

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 two sentences, front-loaded with the essential purpose and the key differentiator (does not become live). Every clause adds value: the event name, the pointer to process_run_get, and the clarification about standing mutation. Zero waste and well-structured.

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 tool has an output schema, return values are covered. The description explains the effect (drafting, appending event) and how to read live standing. It could have explicitly named process_run_standing_commit as the counterpart to make live, but the 'does not become live' phrasing strongly implies its existence. Minor omission, but overall sufficient for an agent to use it 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?

The input schema covers 100% of parameters with clear descriptions for each (due, next, agent, etc.). The tool description adds no additional meaning beyond the schema—it does not explain how parameters relate to 'standing fields' or provide usage hints. Per the baseline rule, when schema coverage is high, a score of 3 is appropriate even with no parameter info in the description.

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 clearly states the tool's purpose: 'Draft standing fields on a run stream' with the critical qualifier '(does not become live)'. It specifies the resource (run stream) and the exact action (appends an event), and explicitly contrasts it with reading live standing via process_run_get, effectively distinguishing it from siblings like process_run_standing_commit. This is specific and unambiguous.

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 gives explicit guidance on when to use this tool: to draft (not make live) standing fields, and tells the agent to use process_run_get to read live standing. It also clarifies that standing is not a separately mutated field, implying this is the appropriate mutation path. This directly informs tool selection and refers to an alternative, leaving no ambiguity.

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