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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds useful context on where the destructiveness lies (whole-document rewrite via `replace`) and the precondition that the document must have been read in full. It still omits what happens on a path collision or whether creation errors when the target exists, which matters for a create tool.

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 front-loaded sentence naming the resource before the conditional case. It is dense but every clause earns its place; only the nested backtick/example phrasing slightly slows parsing.

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 4-parameter mutation tool with no output schema and coverage already provided by annotations and schema, the description covers purpose and the replace path adequately. It leaves out collision/failure behavior and the create-vs-edit boundary, both of which an agent needs to avoid a wrong write.

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 the schema already documents path, store, content and replace, including the same path example and the 'replace an existing document you have read in full' wording. The description adds marginal meaning beyond the schema, mainly the connection between `replace` and whole-document rewrites, so baseline 3 is appropriate.

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 ('Create a document inside an existing Plan') and grounds it with a concrete path example (.plans/<slug>/brief.md). It does not name or distinguish edit_store_document, so the agent must infer that partial edits belong to the sibling, which keeps this at 4 rather than 5.

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?

The description scopes creation to an existing Plan and gives one explicit conditional for the `replace` flag ('rewrite a whole document that was just read'). It never states when to prefer create over edit_store_document or what to do when a document already exists, so usage is implied rather than fully guided.

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