amp_resume

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

With no annotations, the description carries the full burden and does well: it enumerates exactly what comes back, including uncommitted changes and memory-store identity, which the agent could not infer elsewhere. It stops short of stating read-only safety, cost, or volume limits, which matters for an unannotated tool.

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?

Front-loaded with the core value ('where were we?' in one call), followed by the payload list, then usage timing, then the single optional parameter. No filler sentences and nothing repeated from structured fields.

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 one-optional-param, no-output-schema, no-annotation tool, the description covers purpose, timing, and payload contents sufficiently to invoke it correctly. Gaps are secondary: no indication of result size, truncation, or what happens when no resume point exists.

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%, so the description must compensate, and it does: 'file' is described as optional and as a ranking hint ('rank entries about that file first') rather than a hard filter — semantics the bare string/maxLength schema cannot convey. It doesn't specify accepted path formats or matching behavior.

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 resource and scope: it returns the latest resume point, open dead ends, recent decisions/notes, uncommitted changes, and the active memory store. The 'in one call' framing implicitly distinguishes it from granular siblings like amp_read and amp_search, though no sibling is named outright.

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?

'Call it at the start of work in a session' gives a clear triggering condition, and the dead-ends note ('don't repeat them') tells the agent how to act on the output. There is no explicit when-not or named alternative (e.g., versus amp_search for targeted lookups).

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