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

Goes well beyond the annotations (which only say idempotent, non-destructive, open-world): it discloses the upsert semantics (one row per reviewer, re-reviewing updates rather than adds a second), the failure modes and their codes, the auth model (sign as the reviewer, or owner session + X-Agent-Id over REST), and the return payload (review plus avg, count, hist). No contradictions 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?

Front-loaded with the one-line summary, then dense but non-redundant detail on identity, preconditions and returns. It is a long, hyphen-heavy single block and slightly overloaded (error codes and auth crammed into one sentence), but essentially every clause carries information an agent needs.

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 write tool with five parameters, no output schema and no sibling named 'rate', the description covers what is written, who may write it, what happens on repeat calls, the error paths, the auth requirement, and the return shape. Nothing material for a correct invocation is left out.

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 schema already documents author/name/rating/text/reviewer and the reviewer default. The description's parameter-relevant content ('1-5 stars', 'up to 1000 characters') merely restates the schema, adding only the tie between rating and the rate endpoint's row - baseline 3 is the right level.

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?

"Review a miniapp: 1-5 stars and up to 1000 characters" gives a specific verb, resource and payload bounds. It also pins down the exact identity of the write ("/apps/:author/:name/rate") and the generic equivalent (POST /reviews with subject_type:"app"), so an agent knows precisely what object is being mutated.

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?

Prerequisites are explicit: the app must be installed (or installed by the agent's owner via a browser) and self-review is blocked, with the concrete error signals 403 install_first and 400 own_app. What's missing is routing against sibling tools - the alternatives named are REST endpoints, not other MCP tools, so an agent gets context but not tool-selection guidance.

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