SSearch

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

With no annotations provided, the description must carry the full behavioral burden. It discloses the fallback to Common Crawl but omits critical behaviors such as error handling, handling of non-HTML content, rate limits, or whether the page text is truncated. The phrase 'extract readable page text' implies some processing but does not specify limitations.

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 sentence, which is concise and front-loaded with the primary action. However, it is under-specified given the three parameters and lack of annotations. The structure is acceptable, but the brevity leaves out important context, so it does not fully 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?

The tool has no output schema and no annotations, so the description should cover return format, error conditions, and parameter effects. It only hints at the fallback behavior and says it extracts text. An agent cannot infer what happens if the URL is invalid, what max_chars does, or what the output looks like. The description is incomplete for reliable invocation.

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 0%, so the description must explain parameter meanings. It only obliquely references the archive_fallback parameter via 'optionally fall back to Common Crawl', but does not explicitly describe url or max_chars. The names are self-explanatory to some degree, but the description adds minimal value 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?

The description clearly states the verb 'fetch' and the resource 'readable page text', which is specific and distinct from the sibling search tools. It also mentions the optional Common Crawl fallback, but that's behavioral rather than purpose. The purpose is unambiguous and immediately understandable.

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 no guidance on when to use this tool versus the search siblings. It does not state that this is for known URLs while search tools are for discovery. The only hint is the tool name itself, but that is not sufficient. No exclusions or alternatives are mentioned.

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?

With no annotations, the description must carry the behavioral burden. 'Show' and 'would be used' make clear this is a non-executing, read-only planning operation. However, it does not disclose how the three sources are chosen, whether any external calls are made, or what the returned plan contains beyond the two named elements.

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 one concise sentence with the key output front-loaded ('three external sources and cleaned query'). It contains no filler, though the trailing 'that would be used' is slightly vague and could be more explicit.

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 one-parameter planning tool, the description gives the core return content, but without an output schema it omits useful context such as the format of the external sources, the selection rationale, and whether the tool performs any live lookup. This is serviceable but not complete enough for a 5.

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 only defines a 'query' string with no explanatory text, and the description references 'cleaned query,' implying the provided query is raw input that gets normalized. This adds some meaning, but the description does not explain what cleaning entails or the expected query format. Given the single obvious parameter, this is adequate but not fully compensatory.

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 states a specific verb ('Show') and a specific artifact ('the three external sources and cleaned query'), which clearly indicates this is a planning/preview tool rather than an executing search tool. It does not explicitly differentiate among siblings, but the focus on a plan separates it from search_sources, search_web, and fetch_page.

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?

No guidance is given about when to call this tool versus its siblings, nor are any exclusions or alternatives mentioned. The phrase 'that would be used' implies a pre-search planning step, but this is left to inference rather than stated.

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?

With no annotations provided, the description carries the full burden of disclosing behavior. It only states that it lists sources, but does not mention whether it involves network access, what kind of data is returned, or any side effects. This is minimal disclosure for a read-like operation.

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, lean sentence that front-loads the verb and resource. It contains no filler or redundant content, earning each word's 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?

For a simple list tool with no parameters and no output schema, this description is minimally adequate but leaves gaps. It does not clarify what constitutes a 'search source' or what the result structure looks like, which an agent may need to know, especially given the sibling search tools.

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 tool has zero parameters, so the baseline is 4. The description does not need to explain parameters, and the schema trivially covers everything. No additional parameter semantics are necessary.

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 a specific action ('List') and resource ('local and external search sources'), which distinguishes it from siblings like search_web and fetch_page without needing to open schemas. It is concise and unambiguous, though it does not explicitly call out sibling 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?

No guidance is provided on when to use this tool versus the sibling tools (fetch_page, search_plan, search_web). The description only states what it does, leaving the agent to infer when it should be selected over alternatives.

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?

With no annotations, the description carries the behavioral burden. It provides useful context by specifying that the tool searches a 'local/open web index' and returns a 'small reranked candidate set,' which implies bounded, reranked output. However, it does not explain freshness behavior, rate limits, pagination, or whether this is a read-only operation.

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 with no filler. It efficiently communicates the resource, action, and output type while leaving room for 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 tool with three parameters, no annotations, and no output schema, the description is thin. It omits parameter semantics and any routing guidance among siblings, leaving the agent to infer important operational details.

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 0%, and the description adds no direct meaning to the query, fresh, or max_results parameters. The phrase 'small reranked candidate set' loosely relates to max_results, but the description does not compensate for the lack of schema-level parameter docs.

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 states a clear verb ('Search'), a resource ('the local/open web index'), and an output characteristic ('small reranked candidate set'). It does not explicitly differentiate itself from siblings like search_sources or search_plan, but its resource and output type make the core purpose evident.

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?

No explicit guidance is given about when to choose search_web over sibling tools such as search_sources or search_plan. The description implies it is for web-index search, but it does not state when not to use it or which alternatives fit better for related tasks.

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