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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered elsewhere. The description adds only the vague notion of reading "in stretches" — it never says how large a stretch is, what happens when the end of file is reached, whether there is a truncation signal, or what the offset default is when omitted. That is the one behavior an agent most needs for a chunked reader, and it is absent.

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?

A single short sentence with zero padding and the verb front-loaded. It is efficient, though the terseness crosses into under-specification rather than genuine crispness.

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 three parameters, no output schema and no annotation gaps, the description should carry the return-shape and chunking contract; instead it says nothing about what a "stretch" contains or how to continue reading. For a paginated read tool whose whole correctness hinges on offset looping, this is a substantial gap.

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 all three parameters (offset, file_id, document_id) are documented in the schema itself and the baseline of 3 applies. The description adds no meaning beyond that — notably it does not explain what unit or default offset uses, nor clarify that file_id's "p:…" prefix distinguishes it from document_id.

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?

"Reads a project file" gives a verb and a resource, but "in stretches" is idiosyncratic phrasing that never resolves into a concrete concept (chunked reads? pagination?). Sibling read tools such as deck_read_slide, deck_read_source and deck_read_styles are never referenced, so an agent cannot tell from the text why it would pick this one over 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?

There is no when-to-use guidance, no stated prerequisites (does document_id need to be opened first via open_work?), and no alternative named. The only usable hint is the offset parameter, which the agent must infer means repeated calls walk the file.

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