daily_dataDaily data for (station, sensor).
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | ||
| start | Yes | YYYY-MM-DD | |
| sensor | Yes | ||
| station_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | Raw text response from API | |
| format | No | Indicates response is plain text (non-JSON) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations indicate read-only, idempotent, non-destructive, and open-world hints, but the description adds no behavioral details such as date range handling, output granularity, or constraints. Without description, the agent cannot know if this returns a single day's data or a range, or how missing data is handled.
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 description is a fragment, not a sentence, and is under-specified rather than concise. It uses placeholder syntax that could apply to many tools, and while short, it does not earn its place because it conveys almost no actionable 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 having an output schema and annotations, the description is too incomplete for a tool with 4 parameters and time-series semantics. It fails to explain the meaning of 'daily data', the required start parameter's role or end parameter, and what constitutes valid sensor and station IDs. This is well below the minimum viable description for an agent to use the tool 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?
The description vaguely signals that station and sensor are key parameters but does not explain their accepted values, units, or relationships. The schema only documents the start date format (25% coverage), and the description fails to compensate for the undocumented end, sensor, and station_id semantics.
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 "Daily data for (station, sensor)" lacks an explicit verb, essentially restating the title with a parameter pattern. It does not clearly state that the tool retrieves or returns daily measurements, making it vague and largely tautological. It distinguishes from siblings like hourly_data only via the word 'daily'.
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?
No mention of when to use this tool, prerequisites, or relationships to alternatives like hourly_data or event_data. The description provides zero guidance on selecting this over sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools are near-duplicates or have fuzzy boundaries: ask_pipeworx_beta explicitly matches ask_pipeworx exactly, the raw data tools (daily_data, hourly_data, event_data, latest, reservoirs) all read as generic 'get data' operations, and the five polymarket_* scanners overlap in opportunity-finding. The verbose descriptions help for many composite tools, but an agent can still easily select the wrong variant.
The naming is predominantly consistent lowercase snake_case with strong prefixed families (ask_pipeworx*, polymarket_*, pipeworx_*, scan_*) and clear verb_noun actions. Minor deviations like noun-only latest/reservoirs, ask_pipeworx lacking a separator, and generate_llms_txt keep it from a 5.
37 tools is well above the heavy threshold, and the count is inflated by redundant meta-tools, three router variants, six overlapping generic data fetchers, and six prediction-market tools. Many tools are purposeful, so it is not an extreme mismatch, but the surface would be much cleaner at roughly 20-25 tools.
The set covers the core data lifecycle well: discovery (discover_tools, suggest_questions), lookup (ask_pipeworx), grounding/validation (ask_pipeworx_grounded, validate_claim, search_within), entity workflows (resolve_entity, entity_profile, recent_changes, compare_entities), plus memory and subscription CRUD. Minor gaps like no explicit fetch-by-citation tool and a limited subscription type set prevent a 5.