agent_plan

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. Description adds that the tool creates/refreshes a plan, implying mutation. However, it does not disclose side effects like file creation location or whether refreshes overwrite existing data. Minimal extra context beyond 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?

Single sentence that is short and direct. However, the phrase 'expand_request intake' is potentially unclear jargon. Still, no wasted words.

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?

Tool has 9 parameters and no output schema. Description does not explain return values or outcomes. Missing information on what the plan object looks like, whether it is returned or saved only, or any prerequisites. Agents may need to infer behavior from parameter names.

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 schema already documents all parameters. Description adds no additional parameter-level meaning, hence baseline score of 3.

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?

Description uses specific verbs 'create or refresh' and identifies the resource as a 'persisted editable plan with todos from expand_request intake'. It clearly distinguishes from sibling tools like 'plan' or 'orchestrate' by specifying the intake source and persistence.

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?

No guidance on when to use this tool versus alternatives. Sibling tools include 'plan' and 'orchestrate', but the description does not differentiate or suggest contexts. Agent must infer usage from name alone.

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