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

With no annotations, the description carries the full behavioral burden. It does disclose the important trait that output is verbatim sentences kept in original order (no rewriting), but says nothing about determinism, input length limits, or cost.

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?

A single sentence with the method stated first and the return shape immediately after. No filler, nothing that fails to earn its place.

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?

There is no output schema or annotation, but the description effectively explains the return value (N sentences, original order), which is the main thing an agent needs. Only minor gaps remain around input size limits and how ties in 'representative' are broken.

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 coverage is 50%: 'sentences' documents default 3 and max 10, while 'text' is undocumented. The description's 'N most representative sentences' loosely maps N to the sentences parameter but adds no bounds, default, or format detail beyond the schema.

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 operation (extractive summarization) and resource (text), and disambiguates the method as extractive rather than abstractive. No sibling tool overlaps with summarization, so the agent can route to it unambiguously from the name plus first clause.

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 only implied: the agent infers 'use this to condense text' from the name and the word 'summary'. There is no explicit when-to-use, when-not-to-use, or named alternative among the text-processing siblings.

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