AmdpDebugWait

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

No annotations are supplied, so the description carries the burden; it does add real value with the explicit '[read-only]' marker and the constraint that it runs outside batch mode. However, for a long-poll/wait tool the critical behaviors are undisclosed: what is returned if the wait expires with no event (empty result vs. error), whether returned events are consumed or re-readable, and whether the state_handle stays valid.

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?

A single compact sentence with bracketed tags front-loading the read-only and debug classification; nothing is redundant. It is slightly over-compressed, since the fragment omits the verb that would make it self-contained.

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?

There is no output schema, so the description should convey what an 'AMDP event' result looks like and what a timeout yields; it does neither. With full schema coverage on inputs and the detail knob controlling payload size, what remains missing is concentrated in return/timing behavior.

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 100% and every parameter, including the detail enum's three modes, is documented in the schema itself. The description only restates that the wait is bounded by hold_seconds, adding nothing beyond the schema's 'at most 30 seconds' note, so the baseline of 3 applies.

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 names a specific resource (AMDP events of a debug session) and the waiting behavior keyed to hold_seconds, and the '[debug]' tag plus the AMDP prefix separate it from the generic DebugWait sibling. It is a sentence fragment rather than a full verb statement, but an agent can still tell what it retrieves.

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?

Usage is only implied: the '[debug]' tag and 'Runs outside batch mode' tell the agent this is for interactive AMDP debugging and not batch runs, which is a partial when-not. Nothing states when to call AmdpDebugWait versus AmdpDebugStep or DebugWait, nor that a prior AmdpDebugStart/state_handle is required, leaving the agent to infer the polling workflow.

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