Skip to main content
Glama

add_evidence_file

Save log files, command output, or configs as case evidence by path; the server reads the file directly, avoiding retyping its contents.

Instructions

Store a file's contents as evidence, read directly by the server (no need to repeat the text). Use for log files, command output saved to a file, configs. A document you keep rewriting (Q&A notes, analysis, design .md) is not evidence: reference its path instead, and when the engineer adds to it, add_evidence only the new part, verbatim — never store the whole file again. Absolute or ~ path. Not available over the remote door (chat clients) — use add_evidence.

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_id": "<case_id>",
      "path": "<path>"
    },
    "name": "add_evidence_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
case_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden: it discloses that the server reads the file itself (so content is not passed in), the accepted path forms, the incremental-append convention for living documents, and the transport restriction on the remote door. What it does not cover is failure behavior — what happens with an unreadable, missing, or relative path, and whether repeats produce duplicate evidence — which is a meaningful gap for a write tool with no annotations.

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?

Front-loaded with the core action and the server-reads-it property, then the use cases, then the counter-case and the transport caveat. Dense but nearly every clause carries decision-relevant information; the asides about never storing the whole file again lean slightly long but remain actionable.

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?

An output schema exists, so return values need not be explained, and the description covers the behavioral edge that matters most: which files qualify and which should be referenced by path instead. The residual gap is the unexplained case_id parameter and the absence of any error or duplication semantics for a mutation tool.

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 description coverage is 0%, so the description must compensate. It does clarify path ("Absolute or ~ path"), which rules out relative paths, but case_id is never mentioned and the path-parsing behavior for tilde expansion is left implicit. Partial compensation for a two-parameter schema.

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 names a specific verb and resource ("Store a file's contents as evidence") and immediately adds the mechanism that distinguishes it: the server reads the file directly, so the text need not be repeated. That contrast with the inline-text sibling add_evidence is stated outright rather than left to inference.

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

Usage Guidelines5/5

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

It specifies positive cases (log files, saved command output, configs), a negative case (documents you keep rewriting, such as Q&A notes or design .md), the workaround for that negative case (reference the path; add only the new part verbatim), and an environmental exclusion (not available over the remote door — use add_evidence instead). When-to-use, when-not-to-use, and an alternative naming a concrete sibling are all present.

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