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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, and the description adds meaningful behavior beyond those: synthetic orphan rows for forever-paused projects, a server-derived task_retry_available flag, and exact next_tool routing per escalation kind. These are non-obvious behaviors that an agent could not infer from the schema alone.

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?

The description is front-loaded with the core purpose and then packs detailed behavioral information into a compact block. Every sentence contributes useful information, including the project_status contrast and next_tool routing. It is slightly dense but appropriately sized for the complexity of the tool.

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?

Given that an output schema exists and the tool is a read-only list operation with one parameter, the description covers the important behavioral nuances: synthetic orphan rows, retry flag, and next_tool routing. The only notable gap is the lack of explicit documentation for the project_id parameter, but overall the agent has enough context to select and invoke the tool correctly.

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?

The input schema has a single required project_id string with no description, and schema description coverage is 0%. The description mentions project_id only in the context of a synthetic 'orphan:<project_id>' row, but never explicitly explains that the parameter selects which project's escalations to list. The meaning is inferable but not directly stated, which is a meaningful gap for a schema with zero parameter documentation.

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 specific verb and resource: 'See what the work is stuck on' and 'list_escalations' returns each escalation. It clearly distinguishes itself from project_status by contrasting 'only COUNTS open escalations' with 'returns each one with its kind, reason, detail_md, recommended_action...' This gives an agent a precise sense of what the tool produces and how it differs from a sibling.

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 explicitly contrasts with project_status, telling the agent when to use this tool for detailed escalations instead of a count. It also names follow-up tools via the next_tool mapping, which gives helpful routing context. However, it does not explicitly state when not to call this tool or what preconditions (e.g., project existence) apply.

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