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

The description goes well beyond the idempotentHint annotation by unpacking the exact semantics: a retry does not fail or duplicate, it returns the quest already in the file, and the idempotency is scoped to project + title while open. It also discloses the closed-quest edge case and the storage model (quests live in the project's file). No contradiction with the annotations; readOnly=false and idempotent=true are consistent.

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?

Three sentences around 110 words, purpose first, followed by the idempotency behavior and the closed-quest exception. The embedded example makes the concept concrete without adding length, and every sentence earns its place.

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 flat 3-parameter create with 100% schema coverage and annotations covering safety and idempotency, the description is nearly complete: it even sketches the return value (the quest already in the file). The only gap is explicit when-not-to-use guidance against quest-lifecycle siblings, which would make tool selection fully unambiguous.

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 alone documents notes, title, and project_id. The description adds cross-parameter meaning: title is not just display text but the idempotency key alongside project_id, and notes carry the context and links that keep the work resumable. That is genuine added value, not mere repetition.

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 the verb 'add' and the resource (a quest into a project's file), then defines what a quest is in domain terms: 'a next move the customer decided, kept where the work resumes', with a concrete example. This clearly distinguishes it from the many other create_* siblings that target different resources such as projects, corroborations, or surfaces.

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?

Explains when adding a quest is appropriate (when the customer decided a next move) and gives precise retry guidance: calling again while the quest is open is safe and returns the existing quest, while a closed quest with the same title starts fresh history. It does not, however, explicitly route among the quest-lifecycle siblings such as update_quest, complete_quest, dismiss_quest, or reopen_quest.

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