agentsearch-mcp

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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses SSRF-guarding, boilerplate stripping, return envelope details, follow-redirect behavior, and no API key requirement—all valuable behavioral context that annotations alone don't provide.

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 concise sentences that cover purpose, safety, output, and optional parameters without any fluff. Key information is front-loaded, making it easy to parse quickly.

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 description fully explains the tool's behavior, output fields (including redirects and links), safety measures, and authentication requirements. With no output schema, the listed return fields provide sufficient completeness for an agent to invoke 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%, so the baseline is 3. The description mentions links and format but doesn't add substantial new semantic meaning beyond the schema. It adequately complements the schema without redundancy.

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 specific verb 'Fetches' with the resource 'any public http(s) URL' and explicitly describes the cleaning and return of content in text/markdown formats. It distinguishes itself from siblings by focusing on fetching a known URL rather than searching or instant answers.

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 when a specific URL is known and content is needed for an LLM context window, but it does not explicitly compare with alternatives like web_search or state when-not-to-use. Thus, guidance is implied rather than explicit.

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, idempotentHint, and destructiveHint false, covering the safety profile. The description adds valuable context beyond annotations: the normalized answer structure (heading, type, source, etc.), the meta envelope, and the keyless authentication requirement. This goes beyond what annotations alone communicate.

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 three sentences, front-loaded with the tool's purpose, followed by return format and key differentiators (web_search, keyless). Every sentence contributes, with no redundant or filler 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?

This is a simple read-only tool with a single parameter, rich annotations, and no output schema. The description covers the essential behavioral contract (return format, query scope, keyless access) and correctly positions it against siblings. No critical gaps remain.

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% with the 'q' parameter described as 'Query.' The description does not add meaning beyond the schema; it implies the query should be for definitions/entities but does not specify syntax or example formats. Baseline 3 is appropriate when the schema fully documents the parameter.

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 identifies the tool as the DuckDuckGo Instant Answer API for definitions, entities, and quick facts, using a specific verb ('Returns') and resource. It explicitly distinguishes itself from web_search by stating 'Not a full web SERP', so it is uniquely positioned among siblings.

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 explicitly states the intended use case (definitions, entities, quick facts) and directly names the alternative: 'use web_search for that'. This provides clear when-to-use and when-not-to-use guidance, exceeding a vague implication.

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 read-only, idempotent, and non-destructive behavior. The description adds substantial behavioral context: the normalized result structure (position, title, url, snippet, source, domain), the meta envelope (cache state, provider, took_ms), and the provider_required error condition. It does not mention rate limits or pagination, so a 4 is warranted.

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 three sentences, each serving a distinct purpose: stating the core action and provider abstraction, detailing the return envelope, and providing usage guidance. It is front-loaded with the verb and resource, with no fluff or repetition.

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?

Despite no output schema, the description compensates by explicitly listing return fields and the meta envelope. It also covers error handling, provider abstraction, and sibling differentiation. For a 4-parameter tool with robust annotations, this is complete and self-sufficient.

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?

All four parameters are fully described in the schema (100% coverage), so the description need not repeat them. The description adds a minor nuance about the provider parameter ('configured operator-side'), but otherwise relies on the schema. This matches the baseline for high schema coverage.

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 ('Search the web') and identifies the resource (web via a provider-abstracted backend). It explicitly distinguishes from sibling instant_answer by stating 'Use this for a full web SERP; use instant_answer for quick facts/definitions,' making its scope 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?

Provides explicit guidance on when to use this tool vs. instant_answer, and also notes a critical precondition: a provider_required error occurs if no search provider key is configured upstream. This helps the agent decide and anticipate failures.

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