App lifecycle control

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes further by disclosing that the wipe actions are consent-gated and that RN/Expo debug builds may become unable to load their bundle — a real consequence an agent must weigh. It does not describe failure behavior, partial completion, or what state is left behind after a force_stop, which keeps it below a 5.

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 sentence with the general capability front-loaded, followed by the action list in invocation order, with parenthetical qualifiers only where an action needs one. No sentence is wasted and nothing is buried.

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 destructive five-parameter mutation tool with no output schema and only 20% parameter documentation, the description covers the consent and bundle-risk gating well but leaves the consent workflow ('approve' vs 'consentId'), the clear_data/fresh_start distinction, and post-call state undescribed. It is adequate but has identifiable gaps an agent will hit on the destructive paths.

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?

At 20% schema coverage the description must carry the load, and it adds real meaning for 'action' (restart = force_stop + launch) and 'acknowledgeBundleRisk' (accepting bundle-loss risk on RN/Expo). However, 'approve' and 'consentId' are only obliquely covered by 'consent-gated', the difference between 'clear_data' and 'fresh_start' is never explained, and 'sessionId' is untouched.

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 ('control') and resource ('the app under test') and then enumerates the exact seven lifecycle actions it governs, including the compound semantics of 'restart'. An agent can immediately separate this from build, map, flow, or metro siblings without opening the schema.

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?

Gives concrete context for individual actions: 'restart' is flagged as the choice for persistence checks, and 'clear_data'/'fresh_start' are marked destructive, consent-gated, and additionally gated on 'acknowledgeBundleRisk' for RN/Expo. It stops short of naming a competing sibling or stating when not to use the tool, so it is clear context rather than full routing guidance.

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