Condenses text into an extractive summary by scoring and selecting relevant sentences while preserving original order, with Spanish and English stopword support.
Extractive summary: picks the most relevant sentences (word-frequency scoring, ES/EN stopwords) keeping original order. Max 10 sentences.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| max_sentences | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description carries the full behavioral burden and does meaningful work: it discloses the algorithm family (extractive, word-frequency), the language restriction (ES/EN stopwords — a real limitation for other languages), order preservation, and a hard output cap of 10 sentences. It does not address determinism, performance on long inputs, or failure/empty-result behavior, which keeps it below 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero filler, with the method and output-cap constraint front-loaded so the most decision-relevant information arrives first.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (2 params, non-nested, read-only analysis) and an output schema exists, so return values need not be explained. The description covers method, ordering, language support and length bounds, which is close to complete; the remaining gap is explicit sibling routing, which for a summarizer is a minor omission.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 adds the ES/EN language constraint (relevant to the 'text' parameter) and the 'Max 10 sentences' bound, which maps to max_sentences. But the bound is ambiguous: it is unclear whether 10 is a hard cap enforced by the tool or a description of typical output, and the default of 3 and the effect of low values are never mentioned.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource combination ('Extractive summary') and immediately qualifies it with the algorithm used ('word-frequency scoring') and the output invariant ('keeping original order'). This clearly separates it from siblings such as ai_keywords, ai_extract or ai_sentiment, which operate on the same text input but produce different artifacts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by the name and the 'Extractive summary' framing, and the ES/EN stopword detail implies the input language constraint. However, there is no explicit 'use this when... instead of ai_extract/ai_keywords' guidance, and no statement of preconditions (minimum text length, language) that would let an agent route confidently.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.