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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds substantial behavioral context beyond that: the ~15 s sampling interval, the 'throttling = MODERATE or above' threshold, the 60 s minimum before a baseline block appears, frames only when a package is focused, and the explicit limitation that battery drain is not measured.

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-loading is good ('Stop a performance recording and return...'), but the rest is a single dense wall of text mixing return-value fields, thresholds, and caveats with no hierarchy. Given there is no output schema the detail is warranted, but the packing hurts scannability.

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 no output schema, the description carries the full burden of explaining return values, and it does so comprehensively for a complex tool (per-process metrics, derived facts, thermal, baseline, frames). It is only slightly incomplete in not clarifying whether the session is consumed/terminated by the stop.

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?

Only one parameter (sessionId) and schema description coverage is 100%, so the schema already fully documents it. The description adds no format or provenance detail beyond what the schema's own 'Session id from android_performance_record_start' note provides, which is the expected baseline.

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?

States a specific verb ('Stop') and resource ('a performance recording') and immediately enumerates what it returns (time-series, per-process summary, thermal/frames/baseline blocks). This clearly distinguishes it from the sibling android_performance_record_start and android_performance_snapshot without needing to name them.

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 sessionId param note ties it to android_performance_record_start, so an agent can infer this is the closing call of a record session. There is no explicit when-to-use vs snapshot/start guidance, no statement of whether stop can be called twice, and no exclusions.

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