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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint/not destructive; the description goes far beyond that with latency expectations (15-60s, ~90s for thorough), the guarantee that findings are 'never invented' with gaps[], contradiction scans for standard/thorough, citation_uri fetchability guarantees, and hop/re­‑it­era­tio behavior. I see no contradiction between the annotation set and the textual behavior.

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?

Long, but every sentence does work — account routing, scope, mechanics, output guarantees, latency. It is functionally structured: account/tier first, then the core definition, then the alternative, then depth. Slight deduction because the 'what this tool actually does' core phrase arrives mid-first-sentence behind the account requirement, and the paragraph is at the upper bound of what a description should carry.

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 complex research tool with no output schema, it is complete: it pre-describes the findings packet, gaps, contradictions, confidence, source/fetched_at, citation behavior, excerpt semantics, latency, account tiers, and what to expect when the topic is outside the structured catalog. An agent can decide whether to call this tool, how to set depths, and what to do with the response before invoking it.

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 coverage is 100%, so the baseline is 3 — the schema already explains the depth enum and the `question` field in detail. The description adds meaning beyond the schema by tying depth choice to the iteration strategy ('depth:thorough additionally chases leads'), the paid tier, and the one-call resolution of multi-step questions, which helps the agent select the parameter value contextually.

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?

States a specific verb, resource, and scope: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources' with an explicit boundary ('this is NOT open-web search'). It distinguishes itself from siblings — literally naming ask_pipeworx and noting that deep_research is for broad/multi-part questions over structured data while a single lookup belongs elsewhere.

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 both when-to-use and when-not-to-use with named alternatives: 'If you are not signed in, use ask_pipeworx instead', 'For a single lookup use ask_pipeworx', and 'For BREAKING or colloquial CURRENT-NEWS ... prefer ask_pipeworx'. It also tells the agent that depth:*thorough* requires a paid plan, so the agent can avoid recommending it to unauthenticated users.

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