PerMark

search

Read-only

Locate matching sections in Markdown documents using words, short phrases, or tags; retrieve paths and snippets to review AI-written content.

Instructions

Sections matching words (path, line, size_tok, snippet, heading); tags narrow; tags alone list documents.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search"
  }
}

Input Schema

Name	Required	Description
`tags`	No	Only documents with all these tags.
`limit`	No	Sections 1..25, default 10.
`query`	No	Words or a short phrase.
`budget`	No	Max tokens of the answer, 200..12000: fewer hits, shorter snippets.

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv0.7.0Oct 23, 2026

removedInput schema / $schema

Removed value: -"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / budget

Added value: +{
+  "description": "Max tokens of the answer, 200..12000: fewer hits, shorter snippets.",
+  "minimum": 1,
+  "type": "integer"
+}

changedInput schema / properties / limit / description

Previous value: -"How many sections to return (1 to 25). Ten when left out. With `tags` and no `query` it is how many documents\nto list instead (up to 100, twenty when left out)."New value: +"Sections 1..25, default 10."

removedInput schema / properties / limit / format
```
Removed value: -"uint"
```
changedInput schema / properties / limit / minimum
```
Previous value: -0New value: +1
```

changedInput schema / properties / limit / type

Previous value: -[
-  "integer",
-  "null"
-]New value: +"integer"

changedInput schema / properties / query / description

Previous value: -"What to look for: keywords or a short phrase, as you would type them into a search box. Leave it out when you\npass `tags`, to get the documents that have those tags instead of sections."New value: +"Words or a short phrase."

changedInput schema / properties / query / type

Previous value: -[
-  "string",
-  "null"
-]New value: +"string"

changedInput schema / properties / tags / description

Previous value: -"Look only in the documents that have all of these tags, as `list_tags` names them (for example `[\"adr\"]`).\nOptional."New value: +"Only documents with all these tags."

changedInput schema / properties / tags / type

Previous value: -[
-  "array",
-  "null"
-]New value: +"array"

First observedv0.1.0Oct 17, 2026

TDQS

B3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavior beyond that: it discloses the result fields (path, line, size_tok, snippet, heading) and the important mode switch where tags without a query degrade into document listing. It doesn't mention ranking or pagination, which keeps it off a 5.

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

Conciseness3/5

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

It is very short with no wasted words, but the clipped, fragment style ('Sections matching words ...; tags narrow; tags alone list documents') sacrifices readability for brevity. Semicolon-joined fragments front-load the key facts but read more like schema notes than a description.

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?

With no output schema, the description usefully names the return fields, and the four parameters are fully documented in the schema. However, it leaves unclear what a 'section' is relative to the toolset's document model, how results are ordered, and how budget interacts with result count — gaps an agent may hit on first use.

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 100%, so baseline is 3. The description reinforces the tags parameter's narrowing effect and its standalone listing behavior, but adds nothing about budget or limit semantics (fewer hits, shorter snippets) beyond what the schema already states.

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

Purpose3/5

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

The description is telegraphic — 'Sections matching words' — with no explicit verb, but it does convey the resource (sections, not whole documents) and the returned fields (path, line, size_tok, snippet, heading). The dual-mode clause 'tags alone list documents' distinguishes it from a pure document lister, though it never names a sibling such as read or outline.

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?

'tags alone list documents' is the only usage signal: it tells the agent what happens with tags-only input, but not when to prefer this over read, outline, get_context, or list_notes. There are no exclusions, prerequisites, or alternatives named.

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

Deploy Server