Skip to main content
Glama

ReadingRate

Search poems

search_poems
Read-onlyIdempotent

Searches the words of every poem in the ReadingRate collection and returns the matching lines, the lines around each, and each poem's anchor, which get_poem, save_poem_line and annotate_poem_line accept.

Use when the user half-remembers a line, or wants poems that mention an image or a subject, such as "the poem about the shattered statue in the desert". It returns only poems already in the collection; it does not write, continue or translate poems.

It matches words, so a remembered phrase works better than a paraphrase. The poems are in English: for a reader writing in another language, search with the English words a poem would use, explain in the reader's language, and quote the poem's lines in the original English rather than in a translation of your own.

Example: {"query": "the woods are lovely dark and deep"}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of results (default 10, max 25)
queryYesA line, a phrase, or the words remembered
poem_idNoSearch one poem only: its anchor or slug, as for get_poem

Output Schema

NameRequiredDescriptionDefault
noteNoGuidance when the query could not match (e.g. written in a non-English script)
resultsYesMatching passages, most similar first. Empty when nothing matched.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/closed-world, and the description adds real behavioral context on top: word-level (not semantic) matching, the consequence that paraphrases fail, that only in-collection poems are returned, and a cross-language policy for non-English readers. The anchor-return contract with three sibling tools is exactly the kind of cross-tool behavior annotations cannot express.

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 purpose and return shape, then usage, then matching semantics, then a copyable example — a sound ordering with no filler. The cross-language sentence is the longest in the block and is the one an agent is least likely to need on every call, so it is slightly over-weighted for the 10% dimension.

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 needn't be explained, and the hard parts (matching mode, collection scope, language policy) are covered. It says nothing about result ordering, how the surrounding lines are bounded, or how limit interacts with truncation, which are the remaining unknowns for a search tool.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning for the required query parameter ("It matches words, so a remembered phrase works better than a paraphrase") and clarifies what an anchor is and who consumes it. limit and poem_id are left entirely to their schema text.

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?

Specific verb+resource ("Searches the words of every poem in the ReadingRate collection") with the result shape named (matching lines, surrounding lines, anchor). The scope word "poem" plus the note that the returned anchor feeds get_poem/save_poem_line/annotate_poem_line lets an agent separate it from prose-oriented siblings like search_book_content or search_books without opening a schema.

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?

Gives a concrete trigger ("when the user half-remembers a line, or wants poems that mention an image or a subject") with a worked example, and draws a clear negative boundary ("does not write, continue or translate poems"). It stops short of naming the sibling an agent should pick instead for prose or for fetching a known poem, so it lands at 4 rather than 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.