delete_config

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

With annotations already declaring destructiveHint=true and readOnlyHint=false, the description adds a genuinely non-obvious behavioral trait beyond them: changes are staged in the candidate config and require a separate 'commit' to take effect. This tells the agent the deletion is not immediately effective, which is valuable context the structured fields do not convey. No contradiction with 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?

Two sentences of roughly 30 words with the [MODIFIES CONFIG] flag front-loaded for at-a-glance mutability awareness. Every clause earns its place: the first states the action and target, the second adds the essential commit-required caveat. No filler or redundant elaboration.

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 2-parameter tool with complete schema documentation and annotations already covering the destructive profile, the description supplies the one workflow fact an agent cannot derive from structured data: the staged-commit behavior. The only gap is no statement about return values or success indicators, though no output schema exists and delete operations typically yield minimal responses.

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 both parameters are already fully documented with an XPath pattern, a concrete example, and the firewall's conditional requirement. The description's 'specific XPath location' merely restates the xpath parameter's role without adding new semantic detail. Baseline 3 is appropriate since the schema carries the full burden.

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 uses a specific verb ('Deletes') tied to a precise resource ('configuration at a specific XPath location on the firewall'), making the operation unmistakable. This clearly differentiates it from siblings like get_config (read), set_config (write), and the typed delete_* family (which target specific object types rather than arbitrary XPath nodes).

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 implies the tool is for generic XPath-targeted deletions and conveys the workflow context that changes are staged and need a commit, which signals follow-up usage of the 'commit' sibling. However, it never explicitly states when to prefer this over the typed delete_* siblings or set_config, nor does it state any exclusions. The usage guidance is implied rather than explicit.

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