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

With no annotations provided, the description carries the full behavioral burden and delivers: already-submitted items are dropped and echoed back in `alreadySubmitted`, the plan renders as a dashboard checklist that ticks itself off, already-tracked items are reordered rather than reset, and planning costs nothing. It discloses return behavior, side effects, and idempotency — far more than the schema or annotations could convey.

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?

Roughly 220 words, but every sentence contributes a distinct piece — purpose, return behavior, parameter handling, dashboard side effect, reorder-not-reset semantics, workflow scheduling, and cost. The purpose is front-loaded and there is no filler; the lenth is earned by the absence of annotations and an output schema.

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's complexity (4 params, cross-tool workflow, no annotations, no output schema), the description is remarkably complete: it covers when to call, precenditions, what gets excluded, the key return field (`alreadySubmitted`), idempotent reordering, and cost. The only minor gap is the full return shape, and the most consequential part of it is explicitly named.

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%, so the baseline is 3, but the description adds real value: items must be passed in work order with a short reason each, the summary is read by the maker, and the checklist must be 'written from what the platforms in this plan actually demand and what the project is missing, not from a generic template,' with decisions surviving re-plans. This meaningsfuly extends the schema's bare field names.

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 opening sentence, 'Write the run order for a project: which platforms, in what sequence, and why each one is where it is,' gives a specific verb, resource, and scope in one breath. It also distinguishes itself from siblings by naming its workflow position ('Call it after qualify_project') and implying a contrast with record_submission (planning vs. recording).

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?

'Call it after qualify_project, using the `recommended` list it hands back' is explicit when-and-with-what guidance tied to a named sibling. The conditional 'if that response carried `questions`, put them to the maker before you plan: the order depends on the answers, and a plan written on an assumption is one they have to undo by hand' is an explicit when-not with a concrete consequence, and the already-submitted exclusion tells the agent what to leave out.

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