watch

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

Annotations already establish read-only, idempotent, and non-destructive behavior. The description adds non-obvious behavioral context: evaluation happens after the fact, covers every recorded site of one function, requires a focus recording, and treats "nothing checked" as a refusal rather than a pass. No contradiction with annotations.

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 compact and front-loaded with the core concept. Each clause contributes: predicate semantics, evaluation timing and scope, the focus prerequisite, and result interpretation. The phrasing is dense and domain-specific but contains no filler.

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?

With all 6 parameters fully documented in the schema and annotations covering safety, the description covers the main unstated constraints: focus requirement, per-function scope, and the nothing-checked failure mode. An example or explicit output shape would improve completeness, but the core contract is sufficiently clear.

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%, so the baseline is 3, but the description adds meaning beyond the schema: "predicate" and "gdb-style watchpoint" clarify the role of expr, while "at every recorded site of one function" and "needs a `--focus` recording" clarify at/run semantics. The refusal rule also gives practical meaning to near-miss and no-hit 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 operation: evaluates a gdb-style watchpoint predicate over captured state at every recorded site of one function. It distinguishes the tool from a generic search or dump, though it does not explicitly compare against siblings like grep or exceptions.

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 a clear prerequisite ("needs a `--focus` recording") and an interpretation rule ("NOTHING WAS CHECKED is a refusal, never a pass"). However, it never explains when to prefer this tool over alternatives such as grep, tree, flow, or exceptions, so usage selection is left mostly to inference.

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