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

Annotations declare a non-read-only, closed-world mutation, so the agent knows it writes. The description adds only that it 'starts a study' and says nothing about the draft being editable afterward or the irreversible lock applied by register_plan — a fact that only appears in the schema, not the description.

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?

A single front-loaded sentence with no filler, typical of a terse definition. It is appropriately sized but so terse that there is no structure to speak of.

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 mutation tool with a nested required plan object, no output schema, and a workflow shared with register_plan/update_plan, the description omits the lifecycle, what happens on duplicate drafts, and what a successful call yields. Too little for the tool's complexity.

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% and every required field, including the nested pre-registration object, is documented in the schema. The description contributes no additional parameter meaning, so the baseline of 3 applies.

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?

States a specific verb ('draft') and resource ('plan') tied to an open task, which is a coherent purpose. But it doesn't distinguish this from update_plan or register_plan in the sibling list, leaving the agent to infer the draft/register lifecycle.

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?

'Start a study on an open task' hints at a precondition (task must be open) but gives no when-to-use versus update_plan/register_plan, and no statement that a draft precedes registration. No exclusions or alternatives are named.

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