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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes far beyond that by disclosing staging semantics, the commit/revert workflow, the triggered-email-first constraint, and that finished or archived beta projects cannot be edited. It also warns that staged responses return STAGED rows with liveVersionId links, so callers expect ids they did not pass in.

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?

Purpose is front-loaded in the first sentence, then ordering rules, then the constraint, then staging behavior. Dense and mostly waste-free, though the staging/id-echo sentence is long and packs several distinct ideas that could be split for faster scanning.

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 non-destructive reorder mutation with three fully documented params and no output schema, nothing material is missing: ordering semantics, subset behavior, invalid-position rule, staging lifecycle, and edit restrictions on finished/archived projects are all covered.

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 baseline is 3, but the description adds real meaning: stepIds is explicitly a partial subset, listed steps go first, omitted steps land after in unspecified relative order. It also clarifies why returned ids may differ from the ones supplied during staging.

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?

Starts with a specific verb and resource plus scope ('Reorders the steps inside one task'), which immediately separates it from updateTasksOrder (reorders tasks) and updateStep (edits a single step). The operand is named explicitly: 'Pass the step ids in the order the testers should work through them.'

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 clear situational context: the change applies immediately on draft/scheduled betas but is STAGED on running/paused betas, and it names commitTaskChanges, revertTaskChanges and getBetaTasks as the follow-up tools. It does not, however, explicitly route to a sibling for the task-level analogue or state when-not to use it beyond the archived/finished exclusion.

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