Skip to main content
Glama

person_dossier

Build a private per-person profile with notes, facts, images, and sources. Refresh the dossier on each call to keep investigation evidence current without inferring identity or relationships.

Instructions

Build a private per-person profile.json with notes, facts, images and sources.

The file is refreshed when this tool is called. It does not infer a person's identity from a photo or treat co-occurrence as a confirmed relationship.

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>",
      "person": "<person>"
    },
    "name": "person_dossier"
  }
}

Input Schema

NameRequiredDescriptionDefault
caseYes
personYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose useful traits: the file is unconditionally refreshed on each call (overwrite semantics) and the tool refuses to infer identity from imagery or confirm relationships from co-occurrence. However it never says where the file is written, whether existing notes merge or are destroyed, or what permissions/auth is needed for a 'private' artifact.

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

Conciseness4/5

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

Two short sentences, front-loaded with the primary action and the artifact produced. The caveats about identity inference and co-occurrence are tersely stated and earn their place, though the second sentence's relevance to invocation (rather than to the tool's internal analysis quality) is slightly unclear.

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

Completeness3/5

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

For a two-parameter tool with no annotations and no output schema, the description explains what gets produced but not the parameter contracts or storage/refresh consequences. An agent knows the intent but would still guess about what a 'case' value must be and whether prior dossier content survives a refresh.

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?

Schema coverage is 0% for the two required parameters, so the description should explain what 'case' and 'person' mean (identifier vs name, whether the case must already exist, whether the person is created if absent). It only implies 'person' via 'per-person' and says nothing about 'case' at all, so this is a meaningful gap.

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?

A specific verb ("Build") plus a clearly named resource ("a private per-person profile.json") with the artifact contents enumerated (notes, facts, images, sources). An agent can distinguish this from case_note or case_add_fact because it is explicitly the aggregation of a per-person dossier. Slightly held back from 5 because it never names a sibling alternative.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, no prerequisites, and no named alternative for collecting notes/facts instead of building a dossier. The only constraints given (no identity inference from photos, no co-occurrence as relationship) are output-quality caveats rather than selection guidance.

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