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's added value is the ~/.hermes scoping and the existence of saved version snapshots. It does not disclose failure behavior (missing file, invalid version) or how version identifiers are obtained beyond the implied history call.

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?

One sentence with parenthetical mode cues, front-loaded on the default no-path listing behavior. Every clause maps to a distinct invocation mode; nothing is redundant or padded.

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 four-parameter read tool with no output schema and sparse schema descriptions, the description covers all invocation modes and the storage location. The main omission is return shape — whether a file read yields raw content plus metadata, and what a version listing looks like — which matters because no output schema exists to fill that in.

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 coverage is only 25% (only agent_id is documented), so the description must carry the load and largely does: it explains that path selects a file, history toggles version listing, and version selects a specific snapshot, including that the latter two are modifiers of path. It never states the format of a version string or where to get one, which is the remaining gap.

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 names a specific verb and resource and then enumerates all four operating modes with the exact parameter combination that selects each: no path lists files in ~/.hermes, path reads a file, path plus history:true shows saved versions, path plus version shows one old version. An agent knows precisely what the tool does without opening the schema.

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?

Usage is encoded as explicit mode-to-parameter mappings, which is exactly the guidance an agent needs to pick the right call shape. It stops short of naming an alternative such as write_agent_file for mutations or stating when not to use this tool, so it is clear context without exclusions.

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