layerfs_fs_grep

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds that results are paginated, which is genuine context, but it doesn't say what pattern dialect is accepted, what the default page size is, or what happens at the end of pagination.

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 compact sentence with the core verb front-loaded and no filler. It is terse without being wasteful, though the pagination clause dangles without detail.

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 five-parameter tool with no schema descriptions and no output schema, the definition is far too thin; an agent must guess pattern syntax, scoping via ref/path, and paging behavior. Only the existence of pagination is conveyed.

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. It implies pattern and pagination semantics but leaves ref, path, pagePos bounds, and pageSize defaults completely undocumented, and never clarifies whether pattern is regex, glob, or literal.

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?

It gives a specific verb (search) and resource (saved text), but 'LayerFS pattern semantics' is undefined and nothing distinguishes it from the sibling layerfs_fs_glob, which also searches by pattern. An agent cannot tell whether this is a content search or a path search from the text alone.

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 statement of when to use this versus layerfs_fs_glob, layerfs_fs_read, or layerfs_fs_list, and no prerequisites such as whether a workspace mount is required. The only usage clue is the pagination mention.

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