Skip to main content
Glama

Literary devices

gj_literary
Read-onlyIdempotent

Find rhetorical devices and concept tags in Persian poems, including device definitions, tagged couplets, counts, and per-poem annotations; coverage is partial, mostly Hafez.

Instructions

Show rhetorical devices (آرایه: tashbih, esteare...) and concepts tagged in poems; coverage is partial, mostly Hafez.

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": "gj_literary"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNoDevice key or name (tags view), or concept search text.
viewNoLookup when no poem_id: devices (the list with definitions), concepts (search `tag`), tags (couplets tagged with device `tag`), stats (tag counts). Default devices.
cat_idNoLimit tags/stats to this book/category.
poem_idNoRhetorical devices tagged in this poem, per couplet.
poet_idNoLimit tags/stats to this poet.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, so the safety profile is covered. The description adds the one thing annotations cannot: a data-coverage limitation ('partial, mostly Hafez'), which matters for trusting and presenting results. It does not describe result shape per view, which is the remaining gap.

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?

Single sentence, front-loaded with the resource and immediately followed by the coverage caveat; no redundant or filler wording. Slightly dense with the parenthetical transliterations, but nothing is wasted.

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?

With five optional parameters, no required params, a fully described schema, and no output schema, the combination of schema plus this description is nearly sufficient for correct invocation. The only shortfall is that it never explains what each view returns, though the schema's enum descriptions partly compensate.

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% and the view enum is fully documented in the schema, so parameter meaning is largely handled there. The description only adds example values for the device key (tashbih, esteare), which marginally enriches the `tag` parameter – baseline 3 is appropriate.

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?

Specific verb+resource: 'Show rhetorical devices ... and concepts tagged in poems', with concrete examples (tashbih, esteare) that pin down what 'devices' means. It does not name a sibling it is not, but the subject matter (devices/concepts) is distinct enough that an agent won't confuse it with gj_poem or gj_search.

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

Usage Guidelines3/5

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

The 'coverage is partial, mostly Hafez' caveat gives useful selection context (don't rely on this for non-Hafez corpora), but there is no explicit when-to-use guidance and no named alternative for broader lookups. Usage is only implied by the resource described.

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