kratos_docs_ask

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

With no annotations present, the description carries the full burden and does well: it discloses that the question text is transmitted to an external endpoint (mcp.deepwiki.com), that the tool is off by default behind an env flag, and that returned answers may be stale or diverge from the locally installed Kratos build. It stops short of describing latency, rate limits, or failure modes when the flag is unset.

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 sentences, tightly front-loaded: capability first, reliability caveat plus corrective action second, privacy/availability gating last. No filler, and the parenthetical repo note is the only optional clause.

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-shape explanation is unnecessary, and the description covers the things structured fields cannot: external data egress, default-disabled status, and answer staleness. What remains unaddressed is failure behaviour when the env flag is off and roughly how large/slow an answer to expect.

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. It does so for 'question' by characterising it as free-form and giving example question categories (solver settings, process parameters, application behaviour, error meanings). For 'repo' it only hints via '(or another indexed repo)'; the default repo string and what counts as an indexed repo come from the schema alone.

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?

Names a specific verb and resource ('Ask DeepWiki a free-form question about Kratos (or another indexed repo)') and scopes it to conceptual topics like solver settings, process parameters, and error meanings. It distinguishes itself from the authoritative local tools by directing cross-checks to kratos_list_* / kratos_get_process_defaults, though it never names the nearest siblings kratos_docs_read or kratos_docs_structure, so the docs-family split is left implicit.

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?

Gives a clear context for use (free-form/conceptual questions about Kratos) plus an explicit exclusion path: answers may be stale, so verify with kratos_list_* / kratos_get_process_defaults. It also states the operational precondition that the tool is disabled unless KRATOS_MCP_ENABLE_DEEPWIKI=1, which prevents futile calls — only the missing pointer to local docs tools keeps it short of a 5.

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