summarize_content

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

Annotations already declare the safety profile (readOnlyHint, idempotentHint, destructiveHint false). The description adds meaningful behavioral context: it accepts text not URLs, performs extractive or abstractive summarization, leverages Ollama/sampling for abstractive rewrites, and costs 4 credits. This goes beyond what annotations provide, though it doesn't disclose return format or edge-case behavior.

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?

The description is dense but organized: it starts with the core purpose, then input constraint, a usage heuristic, cost, and a concrete example. No sentence is wasted; the structure front-loads the main action and defers cost and example details.

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?

For a two-parameter tool with high schema coverage but an empty options schema, the description covers how to invoke it (text plus optional options), what input type to pass, and an example. It lacks an explicit statement of return value shape, which matters because there is no output schema; however, the core invocation requirements are adequately specified.

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 100% for both properties, but the 'options' property is an empty object in the schema, providing no usable semantics. The description compensates with an example showing summaryLength and summaryType, and clarifies that 'text' should be markdown from a scrape result. This adds real meaning beyond the schema, especially where the schema is empty.

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?

The description uses a specific verb ('condense') and names the resource ('text you already hold'), and distinguishes itself from URL-input tools by stating 'Takes text, not a URL.' It also lists output forms (briefing, comparison, shorter LLM context) and methods (extractive/abstractive), which clarifies exactly what it does.

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?

The description provides explicit when-to-use context: summarizing text already held, and an explicit when-not-to-use: 'Not needed for text short enough to summarise in context yourself.' It also directs users to pass markdown from a scrape result, implying the preceding step. It doesn't name a specific sibling tool as an alternative, but it gives enough routing guidance.

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