Quiet Failures

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

The description adds valuable behavioral context beyond the annotations (readOnlyHint, openWorldHint): 'live' indicates real-time execution, 'Rate-limited per client' discloses constraints, and 'most of the web fails these controls' sets performance expectations. 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?

The description is three sentences, front-loaded with the core action, and every sentence contributes unique information (action, returns, base-rate comparison, rate limit). No fluff 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?

Despite lacking an output schema, the description clearly states the return type ('per-domain breakdown plus a portfolio grade') and notes rate limiting. This is sufficient for a straightforward audit tool, and the comparison to base rates adds decision-making 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?

Schema coverage is 100%, with the parameter description already detailing accepted formats and the 1-50 domain limit. The description's mention of 'up to 50 domains' and 'owns or asks about' adds authorization context but does not enhance parameter structure or syntax. Baseline 3 for high schema coverage 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 specific action ('Live SPF, DKIM and DMARC audit') and resource ('up to 50 domains'). It distinguishes itself from siblings like check_subdomain_takeover and check_whois by focusing on email authentication. The scope ('the user owns or asks about') adds precision.

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 usage context by suggesting comparison to base rates and noting rate limits per client. However, it does not explicitly state when to use this tool over alternatives or provide exclusions. This is clear but lacks the explicit 'use X instead' guidance seen in top-tier examples.

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?

Discloses that the scan is live, enumerates subdomains from CT logs and DNS, tests on 13 cloud providers, may take minutes on large domains, and is rate-limited per client. This adds meaningful behavioral context beyond the readOnlyHint and openWorldHint 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 concise sentences: the first states the process, the second mentions performance and rate-limit constraints. No filler, information is front-loaded, and every sentence earns 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 description covers the scan process and performance constraints well, but lacks an output schema and does not describe the return format (e.g., list of vulnerable subdomains, report structure). This is a noticeable gap for a tool with no 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 already fully describes the 'domain' parameter as 'The apex domain to scan' (100% coverage). The description adds only marginal context like 'one domain' and the scanning process, which doesn't materially enhance parameter understanding.

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 verb-resource-outcome: live scan of one domain, enumerate subdomains via CT logs and DNS, and test for dangling references on 13 cloud providers. This distinguishes it from siblings like check_email_auth and check_whois.

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 clear context that it's a live scan of a single domain with caveats about slowness and rate limiting, implying when this tool is appropriate. However, it doesn't explicitly mention alternatives or when not to use it.

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 mark the operation as read-only (readOnlyHint=true, openWorldHint=true), lowering the bar. The description adds valuable behavioral details beyond annotations: 'Live', 'up to 100 domains', and 'Rate-limited per client'. It does not disclose potential failure modes or response structure, but for a read-only lookup this is acceptable.

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 (two sentences) and front-loaded with the primary action and result. Each clause adds meaning: 'Live' signals immediacy, the domain limit is stated, the purpose (catching lapses) is included, and the rate limit is disclosed. 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 single-parameter read-only tool with no output schema, the description covers the essential operation, constraints (100 domains, rate limit), and a practical use case. It could optionally mention error behavior or that results are per-domain, but the information provided is sufficient for an agent to select and 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%, and the parameter 'domains' already includes details about accepted formats and the 1-100 count. The tool description does not add significant parameter semantics beyond the schema, so the baseline score of 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 uses a specific verb ('live WHOIS lookup') and names the resource (domains) and key outputs (expiry date, registrar, nameservers). It clearly distinguishes from siblings like check_email_auth and check_subdomain_takeover, which address different concerns.

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 a concrete use case ('Use to catch registrations about to lapse') and contextualizes when the tool is appropriate. It does not explicitly name alternatives or exclusions, but the sibling tools are contextually distinct, and the intended scenario is clear.

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, so the safe read nature is known. The description adds behavioral context by specifying that it returns 'matching metrics and their most citable segments,' which clarifies the output focus beyond a generic search. This extra detail justifies a score above baseline.

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 sentences, front-loaded with the core action, and includes practical examples. Every word earns its place, 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?

This is a simple one-parameter tool with no output schema. The description explains what the tool returns ('matching metrics and their most citable segments'), which is sufficient for an agent to understand the outcome. It does not mention edge cases or pagination, but those are not critical for a single-query search tool.

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% and the single parameter 'query' is described as 'Keywords to search for (at least 2 characters)'. The description adds example keywords ('dmarc', 'certificate expiry uk', 'subdomain takeover') but does not significantly enhance meaning beyond the schema, 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 specifies a clear action ('Search'), a resource ('Quiet Failures base rates'), and a method ('by keyword') with examples. It distinguishes from sibling tools like get_base_rate (likely fetch by ID) and list_base_rates (list all) by emphasizing keyword-based search and returning matching metrics and segments.

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 the tool is for keyword search, but it does not explicitly state when to use it instead of siblings like get_base_rate or list_base_rates. There is no mention of exclusions or alternatives, so the usage context is only implied, not 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?

The description goes beyond the readOnlyHint annotation by disclosing exactly what the output includes (measurement, importance, limits, time series, canonical source URL) and clarifying default segment behavior. This provides rich behavioral context without contradicting the read-only nature.

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 sentences, front-loads the core purpose, and packs useful detail without fluff. Every phrase adds value, from the list of output components to the segment type examples.

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 read-only nature, no output schema, and two simple parameters, the description provides a complete picture: what is returned, what parameters do, and possible segment values. It is sufficient for an agent to invoke 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?

The schema already describes both parameters with examples (metric id, segment slug). The description adds further meaning by explaining segment defaults and naming country/company cut examples, enriching the understanding 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 tool returns 'full detail for one Quiet Failures base rate segment', listing specific content like the figure, confidence interval, measurement approach, and source URL. It specifies the metric and segment parameters, and the scope ('one segment') distinguishes it from list_base_rates while the detail level separates it from find_base_rate.

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 for retrieving comprehensive details on a single segment, noting the default segment and available cut types. It does not explicitly name alternative tools or exclusion criteria, but the context is clear enough for an agent to know when to invoke this tool.

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, and the description reinforces this by framing the tool as a read-only catalog. It adds useful behavioral context by specifying that it returns all published base rates and lists the fields included, which helps set expectations for output scope without conflicting 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?

The description is two efficient sentences: the first lists the contents, the second directs users to get_base_rate for detail. Every word contributes to clarity, and the most important information (catalog, contents) is front-loaded.

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?

With no parameters and no output schema, the burden on the description is to explain what the tool returns. It does this thoroughly by naming all fields (metric id, global question, current global figure, sample size, severity, segment slugs) and clarifying the relationship with get_base_rate. This is complete for a simple listing tool.

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 description correctly omits parameter-specific semantics. It still adds value by explaining that the segment slugs are valid input values for get_base_rate, which indirectly clarifies how data from this tool relates to another tool's parameters. Baseline 4 is appropriate for no-parameter tools.

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 it is a 'Catalog of all published Quiet Failures base rates' and enumerates the exact contents (metric id, global question, current global figure, sample size, severity, segment slugs). It also distinguishes itself from get_base_rate by noting that get_base_rate provides full detail on one entry.

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 differentiates this tool from get_base_rate with 'Use get_base_rate for full detail on one', establishing a clear when-to-use vs. when-not-to-use contrast. It also mentions that the segment slugs listed here are valid values for get_base_rate, providing actionable cross-tool guidance.

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