oddsky

find_excursions

Detect dips and brightenings in an astronomical light curve against a running baseline, returning start, end, depth, durations, asymmetry, and gap status. Restrict to a date window for local noise.

Instructions

Find dips (fainter) and brightenings against a running baseline: start, end, depth, ingress/egress durations, asymmetry, and whether the start or end fell in a data gap. Restrict to a window (start/end) to get a local noise level, e.g. for quiet years.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "case": "<case>",
      "series": "<series>"
    },
    "name": "find_excursions"
  }
}

Input Schema

Name	Required	Description	Default
`end`	No
`case`	Yes
`start`	No
`series`	Yes
`k_sigma`	No
`min_depth`	No
`baseline_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Nov 12, 2026

TDQS

B3.2/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden; it does disclose that the tool compares against a running baseline and reports whether start or end fell in a data gap. It still omits operational behavior such as whether the operation is read-only, permission requirements, performance characteristics, or details of how the running baseline is computed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two dense but well-structured sentences, front-loading what the tool finds and following with the windowing use case. There is no redundant or filler wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a seven-parameter analysis tool with no annotations, no output schema, and 0% schema description coverage, the definition is incomplete. It explains the general output features but leaves most invocation semantics and several parameters undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for seven parameters, and the description only partially clarifies start/end as a window and hints at a running baseline. It does not explain case, series, k_sigma, min_depth, or baseline_days, so most parameter meaning must be inferred from names and defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource: find dips and brightenings against a running baseline, with output characteristics such as depth, durations, asymmetry, and data-gap flags. It is clear what the tool does, but it does not explicitly distinguish itself from sibling tools like compare_windows, fold, or periodogram.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides an implied use case for restricting to a start/end window to obtain a local noise level, e.g. for quiet years. However, it does not say when to use this tool rather than alternative sibling analyses, nor does it give exclusions or prerequisites.

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