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

Annotations only say readOnly/openWorld=false; the description adds the operationally critical facts: the URL is signed and expires in 10 minutes, ranges are capped at 400 lines, offsets are absolute UTF-16, and rangeToken is revision-bound. The revision-bound token is exactly the kind of silent-failure constraint an agent needs disclosed.

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 what the tool does and the one-target rule, and each subsequent sentence adds a distinct constraint (cap, token semantics, edit_file handoff, omit case). It is on the dense side and the rangeToken handoff sentence takes effort to parse, but there is no filler.

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?

An output schema exists, so return shape needn't be described, and the description still flags the non-obvious return artifacts (signed URL expiry, rangeToken). For a 4-param tool with a nested lineRange object and a 400-line cap, nothing an agent needs to call it correctly is missing apart from projectId.

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 0%, so the description carries the burden, and it does for most of it: the fileId/path oneOf is explained, and lineRange's startLine/endLine are clarified as inclusive and 1-based with a 400-line cap. The required projectId parameter is never mentioned at all, leaving one real gap.

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 an editable project file') and immediately covers the second mode (signed download URL for private assets), which distinguishes it from list_files/search_files. It also names edit_file as the counterpart for the rangeToken handoff, so an agent can separate read from write 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 an explicit exclusivity rule ('Provide exactly one target: fileId or path'), explicit when-to-use for lineRange ('localized task in a large text file'), an explicit when-not ('Omit lineRange when the full file is required'), and an explicit refinement rule ('Refine lineRange first when only part of the returned range should change'). This is the when/when-not/alternative pattern at full strength.

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