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

Annotations only declare readOnlyHint=true, which the description matches, so no contradiction. The description adds substantial behavior beyond the annotation: files come from the served version not the seed, server.js is included despite never being served to visitors, large files are truncated with truncated=true and bytes reporting the real size, and binary files are reported as binary rather than mangled.

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?

The purpose is front-loaded and every sentence carries load-bearing information: mode behavior, server.js exception, replace-ordering guidance, truncation/binary semantics, and tier routing. Despite its length, there is no filler or repetition.

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 burden of explaining return values and does so for both modes: the file list with size and server-code flag, and file content with truncation/binary handling. It also covers the security-relevant exception (server.js), the tier restriction, and the safe read profile via readOnlyHint, so 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 coverage is 50% (path has a terse description, dropId has none). The description compensates for the gap by fully explaining path's two modes — omitted returns the file list with size and server-code flags; supplied returns that file's content — which adds meaning beyond the schema's "A path from the file list." dropId itself is just a conventional drop identifier shared across the tool family, so the lack of description is acceptable.

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 — "Read what a GRADUATED app actually SERVES right now" — and draws the critical distinction from the seed captured before graduation. It also differentiates from the sibling dropyour_read_content by explicit tier routing, so an agent can pick the right tool without opening either 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 explicit when-to-use: "Use this before dropyour_replace" because a graduated app is replaced WHOLE and current files are needed to avoid overwriting work. It also names the alternative and its selection condition: "Tier 4 only — at tiers 1-3 ... use dropyour_read_content."

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