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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is fully covered by structured data. The description adds real value by explaining that an omitted path yields a folder listing rather than an error, and that folder paths return child documents. It says nothing about pagination or truncation behavior, even though the `offset` parameter implies paged results driven by a `next` cursor.

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?

Two dense sentences with no filler: the resource and its allowed roots come first, followed by the two path-handling rules. Every clause carries operational information an agent needs before calling.

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 three-parameter read tool with no output schema and a fully annotated safety profile, this is nearly complete: it tells the agent what can be read and how path depth changes the result. The remaining gap is result-shape behavior, notably that large documents are returned in chunks and continued via the `offset`/`next` mechanism.

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 each parameter is already documented, and the baseline of 3 applies. The description does go slightly beyond the schema by naming the top-level path roots and clarifying the empty-path case, which the schema leaves implicit via `default: ""`. However, the `store` and `offset` semantics (especially what a `next` cursor is) are left entirely to the schema.

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 and resource ('Read a store document by path') and then enumerates the exact content domains reachable (.plans, .playbooks, .memory, .brand, .projects), which separates it from the write-side siblings create_store_document and edit_store_document. It stops short of explicitly distinguishing itself from read_draft_file, read_guide, or get_design_guide, even though the '.memory' design-guide content overlaps conceptually with those.

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 concrete calling recipes: omit `path` to enumerate top-level folders, and pass a folder path to list the documents inside it. What is missing is any exclusion or pointer to an alternative, such as when to use read_draft_file or get_design_guide instead of reaching into the store for the same content.

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