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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds useful behavior: it specifies supported content types (Markdown, PDF text, etc.) and discloses that text can be truncated, with a pointer to start_index for continuation. No contradiction with annotations.

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 sentences with zero filler. The main action and return types are front-loaded, and the start_index hint is a separate, purposeful clause. Nothing extraneous.

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?

Given the presence of an output schema and the simple nature of the tool, the description covers the essential aspects: what it fetches, what it returns, and how to handle truncation. It does not mention error cases or rate limits, but those are not critical for correct invocation and are partially implied by the annotations.

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% describing all three parameters. The description supplements the start_index parameter by explicitly connecting it to truncated text continuation, which adds semantic value beyond the generic schema description. max_length and url are already well-documented in 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?

The description clearly states the action ('Fetch') and the resource ('one public HTTP(S) URL'), and enumerates the output types. This unambiguously distinguishes it from the sibling web_search (which searches rather than fetches a known URL).

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 implies usage: you should use this tool when you have a specific URL to fetch. However, it never explicitly contrasts with web_search or states when NOT to use it. The only usage hint provided is about start_index for continuing truncated text, which is a parameter-level instruction, not a tool-selection guideline.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side-effect profiles. The description adds context about selecting the 'first available search provider' and returning both source URLs and provider response, but it doesn't disclose potential variability or failure modes. This modest additional context earns a 3 given the annotations carry the main behavioral load.

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 a single, front-loaded sentence that states the action, provider-selection behavior, and return format without any redundant words. It is concise and well-structured, earning a top score.

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 output schema exists (not shown but indicated), so return-value details are presumably covered there. The description covers the core operation and return format, and annotations address safety. It could mention the implication of 'first available provider' (e.g., result variability) but this is a minor gap. Overall, it is sufficiently complete for an agent to call the tool correctly.

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 all six parameters (query, limit, recency, max_tokens, temperature, num_search_results) having descriptions in the schema. The description adds no parameter-specific detail beyond what the schema provides, so the baseline of 3 applies.

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 clearly states the action (run one web query), the resource (through a search provider), and the outputs (formatted source URLs plus provider response). This is distinct from the sibling fetch_url, which implies fetching a specific URL, so the purpose is unambiguous.

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 implies this tool is for searching, but it does not explicitly state when to use it vs. alternatives like fetch_url, nor does it mention exclusions or prerequisites. The context is clear enough that an agent would infer usage, but no explicit guidance is provided.

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