read_text_chunk

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

No annotations are supplied, so the description carries the full burden, and it does deliver one important guarantee: it is non-mutating ('never creates or changes them'). It says nothing about chunking edge cases, such as whether a chunk can split a multi-byte UTF-8 sequence, what happens when the cursor is at or past EOF, or whether the caller must handle continuation.

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 first sentence ('Read a bounded UTF-8 tail or resume from a previous byte cursor') is nearly duplicated by the second ('Use to read a bounded UTF-8 tail (offset -1) or resume at an explicit byte cursor'), so one of the two is wasted. The remaining clause about logs and non-mutation is worth keeping, but the definition should have been a single front-loaded sentence.

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 and parameter coverage is complete, so return-shape explanation is rightly absent. For a small three-parameter read tool that leaves the gaps as: no sibling routing against the crowded text-reading family, and no guidance on cursor chaining across successive chunk reads, which is the core workflow this tool enables.

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 offset, max_bytes and path are already fully documented, establishing a baseline of 3. The prose reinforces the offset=-1 tail semantics and the cursor-resume idea, but adds no meaning beyond the schema, such as how a returned cursor should be fed back into the next call.

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 with explicit modes: bounded UTF-8 tail via offset -1, or resume at an explicit byte cursor. The 'logs and evolving files' framing hints at the distinction from simple whole-file reads, but it never names the obvious siblings it should be compared against (read_text_file, read_text_page, read_text_lines, read_many_text_files), so an agent must infer the routing.

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 a positive use case ('useful for logs and evolving files') and names the two invocation modes, which implies when to reach for it. However, with four other text-reading siblings available, there is no explicit when-not or alternative-routing sentence, leaving the agent to guess between this and read_text_page or read_text_lines.

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