improve_app

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

Annotations already declare readOnlyHint and idempotentHint, so the bar is lower, yet the description still adds real context: no project code runs, no automatic changes, no unmeasured performance claims, and unassessed areas are reported explicitly. It stops short of describing how findings are ordered or what the plan's output structure looks like, 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?

Four tightly packed sentences: purpose first, then usage triggers, then exclusions with named alternatives, then behavioral caveats. Every sentence carries distinct information and the most actionable content is front-loaded.

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 two-parameter, read-only planning tool with no output schema, the description covers what it does, when to use it, when not to, what it will not do, and what the resulting plan contains. An agent has everything needed to select and invoke it correctly.

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 description coverage is 100%, so the path and offline parameters (including the network lookups that offline skips) are already fully documented in the schema. The description adds no parameter-level detail beyond that, so the baseline 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?

States a specific verb and resource: 'Prioritize existing ... findings into a review plan', enumerating the finding domains (security, crash, accessibility, performance, store, dependency) and the plan's contents (prerequisites, expected effects, validation). It is clearly distinguishable from sibling scanners like scan_project and security_audit, which produce findings rather than prioritize 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?

Gives an explicit positive trigger ('what to fix first or how to make the app better overall, across all areas') and an explicit negative one ('Do not use it for upgrade questions'), routing the agent to upgrade_readiness and upgrade_plan by name. Nothing about tool selection is left to inference.

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