technitium_call

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

With no annotations, the description carries the full burden and does substantial work: it separates read from write behavior, defines a two-tier confirmation protocol, enumerates risky operation classes (delete, restore, import, port/listener changes, user disabling, password changes), and states the token is injected automatically and must not be passed. It omits error/refusal behavior when confirm is missing and says nothing about response truncation.

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?

Front-loaded with the core purpose, then the confirmation model, then the discovery pointer. Sentences are dense but each adds a distinct constraint. The paragraph is slightly long and packs token/password handling into a trailing line rather than integrating it with the params discussion.

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?

An output schema exists, so return-value explanation is not required, and the description covers the two things an agent genuinely needs for a generic endpoint caller: the confirmation/auth model and where to look up per-endpoint parameters. The unaddressed max_chars parameter is the main incompleteness.

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 0%, so the description must compensate and it partially does: confirm, confirm_phrase, and params (via 'never guess parameters' and the endpoint_help pointer) are given real meaning. However max_chars is never mentioned, so truncation behavior is undocumented, and endpoint is only illustrated by example rather than explained.

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 states a specific verb and resource: calling any Technitium API endpoint, with a concrete example path (/api/dashboard/stats/get). It does not, however, distinguish this catch-all tool from the many dedicated siblings (technitium_stats, technitium_zones, technitium_blocking), so an agent has no explicit signal about when the generic caller is preferred over a purpose-built wrapper.

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?

It gives clear operative conditions: reads execute immediately, mutations require confirm=true plus user consent, and risky operations require confirm_phrase set to the exact path, with the risky categories enumerated. It also routes parameter discovery to technitium_endpoint_help. It stops short of saying when to use this tool versus the dedicated sibling tools, which is the one clear guidance gap.

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