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

The description goes well beyond annotations by adding detailed behavior: without plan_id returns favorites/newest and library size, replacement policy; with plan_id returns stop counts, depot, next run charges, tries, etc.; explains account_url sign-in; confirms read-only and 'never returns stops.' This adds significant context that annotations only hint at (readOnlyHint) and provides operational nuances.

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?

Although lengthy, the description is dense with necessary information, front-loaded with the main purpose and then systematic breakdown of modes. Every sentence adds value—no filler, and the structure (purpose, mode-specific behavior, user-summarization rules, usage exclusions, follow-up action) makes it easy to scan.

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?

The description covers both operational modes, user-facing summarization semantics, edge cases (library replacement), authentication for account_url, and cross-tool routing to optimize_routes. Given the tool's complexity and the presence of an output schema, this is complete—nothing an agent needs to call and interpret results is missing.

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 coverage is 100%, but the description adds deeper meaning: explains how limit behaves (favorites first), query filters by name, and plan_id triggers a different return set including last_agent_run. It also clarifies the meaning of next_optimize_charged in the output, which is not in the schema but essential for correct user summarization.

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 explicitly states 'List the plans in the connected Vepathos account' and differentiates behavior with and without plan_id. It also distinguishes itself from sibling tools by noting it is for saved plans, not scheduled tasks, and names alternatives when needed. This is a specific verb+resource with clear scope.

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 explicit when-to-use guidance: 'If they ask for their Vepathos tasks, jobs or functions, call this (saved plans), not the host's scheduled-task list' and 'To rerun or vary one, confirm last_agent_run with the user and call optimize_routes with plan_id.' It also explains summary behavior with next_optimize_charged, giving clear context on when to use this versus alternatives.

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