summarize

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

With no annotations supplied, the description carries the full burden and does meaningful work: "Pure, deterministic, and idempotent" effectively declares a no-side-effect, repeatable read operation, which is exactly the property an agent would otherwise want from annotations. The method (term-frequency scoring, extractive rather than abstractive) further sets expectations about output fidelity, though error behavior on oversized input is left to the schema.

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?

Three sentences, each load-bearing: the first defines method and output, the second gives the use case, the third states behavioral guarantees. The purpose is front-loaded and there is no filler or repetition of schema content.

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 low-complexity, two-parameter tool with no annotations and no output schema, the definition covers method, use case, and side-effect profile. The only modest gap is that it does not describe the shape of the returned result (e.g., ordered list of sentences), which matters slightly since no output schema exists.

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 100%, with both 'text' (50,000-char cap) and 'num_sentences' (1-10, default 3) fully documented in the schema, so the baseline is 3. The description adds only the notion of "most informative, central sentences" as the selection criterion, without extra detail on the optional parameter beyond what the schema states.

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 names a specific verb and resource: extractive summarization of long articles/documents based on term-frequency scoring, and clarifies it returns central sentences rather than abstractive rewrites. That is far more precise than a restatement of the name. It does not, however, reference any sibling tool (e.g., web_reader or pdf_extract as upstream sources), so it stops short of full differentiation.

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?

It offers one explicit usage cue: "Use to compress long context into key points." That tells the agent a triggering condition but gives no when-not guidance, no input-size prerequisite beyond the schema's 50,000-character cap, and no mention of how it relates to siblings that fetch or extract long text.

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