Detect threshold-crossing spikes in broadband neural recordings, reporting precision and recall when ground-truth spikes are available.
Threshold-crossing spike detection on a broadband snippet (max 10 s).
Where the session has ground-truth spikes, precision and recall are reported.
| Name | Required | Description | Default |
|---|---|---|---|
| t0 | No | ||
| duration_s | No | ||
| session_id | Yes | ||
| threshold_sigma | No |
Changes observed during successful MCP inspections.
v0.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of disclosing behavior. It mentions the 10 s snippet limit and conditional precision/recall reporting, but does not disclose what the tool returns, whether it modifies any state, or how it behaves without ground truth. The behavioral coverage is thin and incomplete.
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 extremely short with no fluff, using two concise sentences that front-load the core purpose. It is efficiently written, though the brevity contributes to the incompleteness. Conciseness itself is well executed, but structure lacks additional sections.
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?
Given the tool's complexity (4 parameters, no output schema, no annotations), the description is grossly inadequate. It does not explain return values, parameter semantics, or provide any usage context. An agent would have no idea how to invoke this correctly or interpret results. This is a serious deficiency.
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% and the description provides no explanation of any parameter. t0, duration_s, session_id, and threshold_sigma are entirely unexplained. The description adds zero value in helping an agent understand parameter meaning or units. This is a critical gap.
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 (detect), resource (spikes), and method (threshold-crossing) on a broadband snippet with an explicit maximum duration. It implies a distinct function from sibling tools like sort_spikes or get_firing_rates, though without naming them. The purpose is clear but not explicitly differentiated from alternatives.
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 guidance on when to use this tool versus the many sibling tools. The only situational hint is the conditional reporting of precision/recall when ground truth exists, but it does not indicate when threshold-crossing detection is preferred over other spike processing tools. Lacks explicit when-to-use or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.