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

Annotations only state readOnly=false, idempotent=false, and destructive=false, so the description carries the behavioral burden. It discloses the returned new epic uid, how other tools consume that uid, and that multiple sub-resources can be created in the same call. The mutation effect is clear from 'Create', though explicit side-effect notes are absent.

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?

Four tightly written sentences with zero filler: required fields and the markup constraint are front-loaded, while cross-tool return semantics are delivered at the end. 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 10-parameter write tool with no output schema, the description covers required fields, the AHM prerequisite, assignee discovery, bundleable resources, and the UID return value. Optional fields like color and dates are self-explanatory from the schema; explicit error/permission notes would be the only notable gap.

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 90%, so the baseline is 3. The description mostly restates schema facts such as required fields, AHM formatting, and list_project_users for assignees. It adds cross-tool uid semantics but little new per-parameter meaning beyond what the schema already documents.

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 opens with a concrete verb+resource: 'Create an epic on a project,' and immediately clarifies that only project_id and name are required. It does not explicitly contrast with sibling create/update tools, though mentioning that the returned uid is consumed by create_card/update_card and create_roadmap_slot gives useful role differentiation.

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?

It gives actionable invocation context: read get_ahm_spec before writing description, source assignee uids via list_project_users, and optionally bundle checklists/links/attachments in the same call. It stops short of explicit 'use X instead' or when-not conditions, so it earns a 4 rather than a 5.

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