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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real behavioral context beyond that — the write is 'Staged' (not applied immediately) and 'asks no human' (no approval gate), plus the ${{ SERVICE.KEY }} interpolation rule for file contents. It stops short of saying what 'staged' means downstream (when it reaches the running workload) or whether existing files are overwritten or merged.

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?

Three compact sentences front-loading the main effect before the optional mount and the interpolation note. The clipped fragments ('Staged. This call asks no human.') are terse but each carries information; minor cost in readability rather than waste.

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 10-parameter mutation with a nested files object and no output schema, the description covers the critical unknown behaviors (staging, no approval, variable interpolation, mount target). The remaining gap is write semantics on re-write — replace vs merge of file contents — which matters for repeated calls.

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 80%, so most parameters (config, service, path, mode, expect_revision) are already documented. The description contributes the one genuinely new piece — that file contents may interpolate ${{ SERVICE.KEY }} — but says nothing about uid/gid/mode application or the concurrency semantics of expect_revision. Baseline 3 fits given the schema carries most of the load.

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?

Specific verb+resource: 'Write files into a Config, creating it if needed, and optionally mount it into a Service at a directory' tells an agent exactly what happens and the two effect targets (Config and Service mount). It is naturally distinct from siblings like config_remove/config_rename, though it never names them.

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?

Implies usage through 'creating it if needed' and the optional mount pairing with service/path, and 'This call asks no human' hints at the approval-free path. But there is no explicit when-to-use/when-not vs other tooling (e.g. deploy for applying staged config), leaving routing to inference.

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