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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds important constraints: supports only JPEG/PNG/WebP, explains the @ prefix stripping for image_source, and discloses that it's LLM-powered. It does not describe return format or side effects, but for a read-only analysis tool these are less critical.

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 compact and well-structured. It front-loads a clear usage directive, then provides a capability statement, format constraint, and parameter details. Every sentence contributes useful information without unnecessary fluff.

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 with only two parameters and no output schema. The description adequately covers purpose, usage, and input constraints. However, it does not explicitly state what the tool returns (e.g., a text description or analysis result), which is a notable gap given the absence of an output schema.

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?

The schema covers both parameters at 100%, so the baseline is 3. The description adds value by detailing the allowed forms of image_source (URL, local path) and the @ prefix rule, which is not present in the schema. This additional context justifies a 4.

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 tool's purpose with specific verbs ('analyze, describe, or extract information') and identifies the resource (image). It distinguishes itself from the sibling tool 'web_search' by focusing exclusively on image content interpretation.

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 explicitly says 'You MUST use this tool whenever you need to analyze, describe, or extract information from an image,' providing clear trigger conditions. However, it does not mention explicit when-not-to-use cases or alternatives beyond the implied contrast with web_search.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states that it returns a JSON object with search results but does not disclose rate limits, result count, failure behavior, or safety implications. The search strategy tip about rephrasing is a behavioral note, but the overall transparency is limited.

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 organized into clear sections (Args, Search Strategy, Returns) and is not overly long. The opening imperative 'You MUST' is somewhat redundant but the overall structure is efficient. It earns a 4 for clear structure with minor excess.

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 simple one-parameter search tool, the description is largely complete: it explains the query, provides a strategy, and states the return type. It lacks output schema details but that is not mandatory here. The sibling context is clear, making the description sufficient overall.

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?

The schema covers the query parameter with a description, and the description reiterates that guidance. It adds the extra tip to include the current date for time-sensitive topics, which provides useful semantics beyond the schema. Since schema coverage is 100%, baseline is 3, and the added date advice nudges it to 4.

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 it is a web search API for real-time/external information, using the analogy 'works just like Google Search.' This distinguishes it from the sibling tool 'understand_image,' which handles image understanding. The verb+resource is specific: search the web.

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 explicitly instructs 'You MUST use this tool whenever you need to search for real-time or external information on the web,' providing clear when-to-use criteria. It also includes a search strategy for rephrasing queries if no results are returned. However, it does not explicitly mention alternatives beyond the sibling context, so it earns a 4 rather than 5.

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