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

Annotations already declare readOnly/idempotent/non-destructive, so the description rightly spends its budget elsewhere: it discloses the login requirement and the default filter semantics (ACTIVE + PARKED unless narrowed), which annotations do not convey. It does not describe pagination or ordering behavior, but the added auth and default-filter context is solid value.

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?

Two compact bracketed sentences, front-loaded with the login/domain tag and then the composition chain. No filler; every clause conveys a distinct constraint or routing hint.

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 simple read-only list tool with one optional enum param and no output schema, the description supplies the auth gate, the default scope, and the key returned handle (composeId) plus its consumers. Nothing essential to correct invocation 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 already 100% for the single status enum, so the baseline is 3. The description earns the extra point by documenting the omitted-parameter default (both statuses returned), which the schema does not state and which directly affects how the agent calls it.

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 a specific verb+resource (list my unfinished activity drafts) and scopes it to the host-activity domain. It also names the downstream chain (get/update/publish_activity_draft), which cleanly separates it from the many sibling list_* and get_activity_draft tools.

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?

Clear context for use: retrieve drafts, with the default covering both ACTIVE and PARKED and the option to narrow to one. It also points to the follow-on tools once a composeId is obtained. It stops short of explicit when-not-to-use exclusions versus list_activities/list_my_activities, so a 4 rather than 5.

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