read_file

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

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses chunking semantics, byte-based addressing, maximum chunk size, base64 preservation of exact bytes, consistency checks across chunks, and access boundaries such as canonical bodies and Discussion being unavailable. None of this contradicts the 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?

Four short sentences front-load the core purpose first and then supply only high-value constraints and usage details. There are no redundant phrases or explanations that duplicate the schema or annotations.

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 stateful chunked-read tool, the description covers the full invocation loop: read, follow next_offset, validate consistency, restart, size and encoding limits, and permission/resource exclusions. An output schema is present, so return-value shape does not need to be described in prose.

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?

With schema description coverage at 0%, the description carries the burden. It adds critical parameter meaning: offset and length are byte-based, length has a 262144-byte cap, and base64 encoding preserves bytes. It does not explicitly define path or project_id, but those are reasonably inferable from the tool name and schema titles.

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?

The description opens with a specific verb-resource pair: 'Read an allowlisted governance document in chunks.' It goes on to precisely bound the resource, name the alternative read_discussion, and enumerate what is 'never available', so an agent can distinguish this from sibling tools like fetch or list_files.

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?

It gives explicit protocol guidance: offsets and lengths are bytes, one should follow next_offset to EOF, compare size/modified_ns and restart on change, and respect the 262144-byte maximum chunk. It also states the exclusion for Discussion and points to read_discussion as the proper alternative, so there is no ambiguity about when to invoke this tool.

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