jef-mcp

Ask Jef to pick one

jef_pick

Read-onlyIdempotent

Choose among 2 to 5 user-provided options, returning one with a confidence score to break decision deadlocks.

Instructions

Pick one of 2 to 5 options and give a probability for each. Use this when the user is stuck between named choices and wants one chosen for them: dinner, which film, which of three plans. Jef can only ever return an option you passed in, so it cannot introduce an idea of its own.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`options`	Yes	The candidates. The answer is always one of these, exactly as written.
`question`	No	Optional context, such as "what should I cook tonight". Affects the answer but is not read.

Output Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Which decision shape was used.
`answer`	Yes	One of the options you passed in, copied exactly.
`blocked`	Yes	True when the input contained profanity, slurs or sexual content. Nothing was stored or echoed. Do not retry.
`ranking`	No	The options in order, best first. Null unless the shape was order.
`cost_usd`	No	Always 0. There is no billing.
`thoughts`	No	Always 0.
`escalated`	Yes	True when the input touched health, harm, money, law or safety. Tell the person to ask a human. Do not rephrase and retry.
`confidence`	Yes	0.84 to 0.99 normally, exactly 0 when escalated or blocked. It is not calibrated and means nothing.
`latency_ms`	No	Negative. Jef answers before you ask.
`tokens_read`	No	Always 0. The input is hashed, not read.
`probabilities`	No	One entry per option, percentages summing to 100. Null unless the shape was pick.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.7Sep 19, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds the key behavioral guarantee that Jef cannot introduce new options ('only ever return an option you passed in'), and that it outputs probabilities. It does not elaborate on the behavior of the optional question parameter beyond the schema's note, but it adds meaningful constraint disclosure.

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 sentences long, front-loads the primary action and output, gives concrete usage examples, and adds a single crucial constraint. No redundant or filler language. Every sentence serves a purpose.

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

Completeness4/5

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

The tool is simple with two parameters, full schema coverage, and an output schema (present). Annotations cover safety (readOnly, idempotent, non-destructive). The description covers purpose, usage, and a key behavioral constraint. It does not explicitly state what the question parameter does beyond the schema, but that is already documented. Overall, nothing critical is missing for an agent to call it correctly.

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

Parameters3/5

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

The input schema provides full descriptions for both parameters (100% coverage). The description does not add any parameter-specific meaning beyond what the schema already states; it only reiterates the constraint that returned options are from the passed list, which is already in the options description. Thus, the description does not need to compensate, so a baseline of 3 is appropriate.

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

Purpose5/5

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

The description opens with a specific verb ('Pick') and resource ('one of 2 to 5 options') and states the output ('give a probability for each'). It clearly distinguishes from siblings like jef_rank or jef_yes_no by specifying the scenario of 'stuck between named choices.' The constraint that it only returns passed-in options further clarifies scope.

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

Usage Guidelines4/5

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

The description explicitly states when to use it ('when the user is stuck between named choices and wants one chosen for them') with concrete examples (dinner, film, plans). It does not explicitly name alternative sibling tools, but the examples imply the use case is distinct from ranking or scoring. This is clear but could benefit from explicit exclusions.

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

Deploy Server