set_config_value

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

Discloses that changes apply immediately, are reversible (undo restores prior subtree), and that admin subtree is refused, even under dry_run. This goes well beyond the raw schema and compensates for missing annotations.

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?

The format is front-loaded with a clear summary, then behavior, then refusal, then a clean Args list. No filler; each sentence adds essential information.

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?

Despite no annotations or output schema, the description covers purpose, caveats, parameter semantics, and error behavior (refusal reporting). It is complete for an agent to invoke correctly.

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?

With 0% schema description coverage, the description fully compensates: it explains path (slash-separated, example), value (JSON), insert (insert vs replace with rationale), dry_run (preview), and target (proxy target name, default omitted).

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 '[WRITE] Set a caddy config subtree' providing a specific verb and resource, with an example (route's upstreams). It distinguishes itself from sibling read/delete/load tools by framing the action as a reversible write.

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?

Explicitly states that paths come from search_config/list_routes, that this is inappropriate on traefik/haproxy ('raises the support matrix's teaching error'), and that the admin subtree must be modified in caddy's own config file instead. It also explains when to use insert (re-creating a deleted array element).

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