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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds two genuinely new behavioral facts beyond the annotations — that content is returned line-numbered and that a whole-file sha256 is produced — which matters since there is no output schema. It stops short of pagination behavior (limit max 2000), binary/image handling, or missing-file errors.

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?

Six words is not concise, it is underspecified — this is a fragment with no lead sentence, no verb, and no structure to front-load. The brevity saves nothing because the agent still has to guess the operation.

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?

A five-parameter file-read tool with no output schema and no parameter documentation needs a real description. Even with annotations covering the safety profile, the agent cannot tell what pagination does, whether images are handled differently, or what path is relative to.

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 0% across five parameters, so the description carries the full burden and provides none of it. Nothing explains workspace, build_id, path semantics, or what limit/offset measure (lines vs bytes) or what the defaults are.

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 is a noun phrase, not a verb phrase: it names output characteristics ("numbered text/image", "whole-file sha256") rather than stating that the tool reads a file. An agent can infer 'read' from the tool name and the annotation title, but the description itself does not distinguish this from siblings like files_list, files_diff, or files_search.

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 mention of when to pick files_read over files_list/files_search/files_diff, and no preconditions such as needing a build_id or workspace. Nothing is misleading, but nothing helps routing either.

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