agent-tools

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

Annotations already declare readOnlyHint=true, and the description adds context about the data source ('Dati dal monitor live di Sequel') and the nature of the response (confirmed updates and current rollout). This goes beyond the annotations without contradicting them.

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 tightly worded sentences in Italian: the first states the core functionality, the second cites the data source. No redundant information or repetition of schema 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 one optional parameter and no output schema, the description fully explains what the output covers (latest confirmed updates and current rollout status). The data source and language default (via schema) complete the context.

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 only parameter 'language' has full schema coverage with description ('Lingua della risposta (default it)'). The tool description does not add extra semantic detail beyond the schema, matching 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 clearly states the tool 'riporta gli ultimi update di ranking confermati ufficialmente da Google e indica se ce n'è uno in rollout' — a specific verb and resource, distinguishing it from siblings like quick_site_check and search_insights.

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 a clear use case: checking official Google ranking updates and current rollout status. It doesn't explicitly name alternatives, but sibling tools are clearly different domains, so context is unambiguous.

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 provide readOnlyHint: true and openWorldHint: true. The description adds valuable behavioral context by listing the exact checks performed and the type of output (mini-verdict), going beyond the annotations. No contradictions 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 efficiently convey the purpose, the specific checks, the output type, and a pointer to the full tool. Every word earns its place; no filler or redundancy.

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 2-parameter read-only tool with annotations, the description sufficiently covers the core functionality, lists the checks, and notes its abbreviated nature. Even without an output schema, the 'mini-verdetto' term sets expectations. It could specify the verdict format but is otherwise complete.

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?

Input schema coverage is 100% with clear descriptions for url and language. The description adds no new parameter details beyond what the schema already provides, so baseline 3 is appropriate.

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 performs 4 essential AI agent readiness checks (robots.txt, AI bot/Content-Signal rules, llms.txt, structured data) and returns a mini-verdict. It uses a specific verb ('Esegue') and resource ('prontezza per gli agenti AI su un sito'), and explicitly distinguishes itself from Sequel's full agent-ready tool.

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 marks the tool as a quick sample ('È un assaggio') and points to the full report on the agent-ready tool of Sequel. This provides a clear when-to-use vs. when-not-to-use distinction, guiding the agent toward the appropriate tool for full analysis.

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 provide no positive hints (readOnlyHint, idempotentHint, etc. are all false), so the description carries the burden. It discloses that the team responds via email within one business day, which is useful, but it does not describe the immediate effect of the submission, such as whether a confirmation is returned or how data is handled.

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 two concise sentences that front-load the action (send quote request), the recipient, the scope of services, and the expected response. No superfluous text.

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 covers purpose, target, services, and response method, which is sufficient for a simple form-submission tool. It does not describe the immediate tool output, but with no output schema and the email response noted, it is adequately complete.

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 all six parameters well-described. The description's mention of service types loosely maps to the 'need' parameter but adds no new semantic detail beyond the schema, aligning with the baseline for high 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 clearly states the tool sends a quote request to Sequel Consulting and lists the service categories (SEO, GEO/AI visibility, etc.). It distinguishes itself from sibling tools, which are about checking status or site information, by being the only tool that submits a quote request.

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 gives clear context for when to use the tool: to request a quote for specific consulting services. However, it does not explicitly mention alternatives or state when not to use it, leaving some implicit guidance.

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 declare readOnlyHint=true, so the safe, read-only nature is already conveyed. The description adds valuable behavioral context by specifying the return payload: the 3 most relevant contents with links, including a Markdown variant. This goes beyond the annotations without contradicting them.

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 two concise sentences, front-loaded with the action and resource, and contains no redundant or irrelevant text. Every clause adds value, from the scope of searchable content to the specific result count and Markdown output option.

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 search tool with a 100% covered schema, readOnly annotation, and no output schema, the description fully covers what the tool does, what it searches, and what it returns (3 links, optionally in Markdown). It is self-sufficient and leaves no major gap for the agent to infer.

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%, meaning both 'query' and 'language' are already well-documented with examples and constraints. The description adds no additional parameter-level detail, so it meets the baseline but does not elevate it. The mention of returning 3 relevant contents is a result trait, not parameter semantics.

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 ('Cerca tra gli articoli... e le pagine servizi/strumenti') and identifies the specific resource set (Sequel Observatory articles and services/tools pages) along with covered topics. It also distinguishes itself from siblings like google_updates_status by focusing on content search rather than status monitoring.

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 by describing what is searched and the result format, but it does not explicitly state when to prefer this tool over alternatives or when not to use it. There is no mention of exclusions or comparison to siblings like quick_site_check or request_quote, so the guidance remains implicit rather than explicit.

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