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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds genuine behavioral context beyond that: each row reflects the CURRENT version (what the bundle endpoint serves right now) and a count of versions behind it, which tells the agent what the data represents dynamically.

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-loads the key distinction (collapsed view) in the first clause, then explains row content and alternatives. Two dense but waste-free sentences; every clause earns its place.

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?

No output schema exists, so the description usefully explains what each row contains and what the version count means. It stops short of describing pagination semantics (offset over the flat list), which the schema hints at, so it's nearly but not fully complete.

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% with 4 well-documented parameters, so the schema carries the load and baseline 3 applies. The description echoes the author+name grouping concept but adds no format, default, or filtering detail beyond what the schema already provides.

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+resource ('Browse the miniapp market') and precisely defines the projection: one row per app (author+name) rather than one row per published version. This directly distinguishes it from the sibling list_apps, so an agent can pick between them without opening schemas.

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 a clear condition for using this collapsed view and routes related needs explicitly — 'use GET /apps/:author/:name/versions for the full history and POST /apps/:author/:name/rollback to change which one is current.' It doesn't name the flat sibling (list_apps) directly, so selection isn't spelled out exhaustively, but the contrast plus alternative endpoints is strong guidance.

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