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

Beyond annotations (which only mark readOnly/destructive/idempotent false), the description reveals critical behavior: edges are never erased, re-adding reinstates the original edge, archiving does not release the dependency, and task-level edges are non-blocking. It also documents stable rejection codes, giving the agent a full behavioral contract.

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?

Every sentence in the description carries essential information—purpose, mutation semantics, idempotent-like re-add behavior, unblocking condition, epic-only gating, and error codes. It is dense but front-loaded with the core purpose, and no sentence is redundant.

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?

The description is thorough for a mutation tool with no output schema: it covers edge lifecycle, scope restrictions, and error codes. However, it does not describe the success return payload or explicitly define 'owned', so a small gap remains for agents that need to interpret the result.

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 0%, but the description compensates by defining the relationship: ticket_id is the dependent ticket, depends_on_ticket_id is the prerequisite. The mention of dependency_self and dependency_duplicate error codes clarifies that the IDs must be distinct and that duplicate edges are rejected, adding meaning beyond the bare UUID schema.

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 states a specific action ('Record that an owned ticket cannot complete until another owned ticket is done') and clearly differentiates from the sibling ticket_dependency_remove by explicitly naming it as the correction path. This leaves no ambiguity about what the tool does.

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 explicitly guides when to use this tool vs ticket_dependency_remove, explains the consequence of re-adding a prerequisite, and notes that only epics are gated, so the tool records but does not block for tasks. It provides clear context for the edge case of archiving and error codes.

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