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

Adds substantial behavior beyond the annotations: lookups run from this machine via the user's resolver (not a third-party API), SPF include/redirect chains are followed up to 25 queries, and no rate limit exists beyond the resolver's. Annotations only say read-only/open-world/idempotent, which would not convey any of this.

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?

Front-loads what is checked and how lookups happen, then triggers, then the DKIM caveat. Parenthetical detail is dense but each clause adds operational meaning; slightly long-winded in the resolver explanation.

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 two-parameter read-only tool with no output schema, it covers execution model, query budget, and the main failure mode (unproven DKIM). It stops short of describing the shape of results (per-record pass/fail, recommended fixes), though the trigger sentence about 'exact DNS fixes' implies it.

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%, so the baseline is 3; the description earns extra by explaining the semantic consequence of omitting dkimSelectors (only common selectors probed, so DKIM absence cannot be proven) and where the value comes from (s= in a real message's DKIM-Signature header).

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?

States a specific verb (check) plus the exact resources inspected (SPF, DMARC, DKIM, MX), and the title/sibling set makes it distinguishable from the SEO/MRR tools. An agent can tell this is a DNS email-auth diagnostic without opening the schema.

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?

Gives three concrete trigger scenarios (mail landing in spam, before launching a sending domain, producing exact DNS fixes) and explicitly names the alternative path for definitive DKIM results (pass dkimSelectors). No exclusions are stated, but none are needed for a read-only diagnostic.

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 non-destructive behavior, so the safety profile is covered. The description adds genuinely non-structured context: money is returned in cents plus currency, and unverified figures carry a flag that must never be presented as verified revenue — a real presentation constraint.

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?

Five short sentences, front-loaded with what the tool returns, then the optional filter, then the data-format and verification caveats. Nothing is redundant with the annotations or schema.

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?

No output schema exists, and the description compensates by describing the return shape (cents plus currency, per-row verification flag). Limit/pagination behavior is left entirely to the schema, which is acceptable given its coverage.

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%, with limit range and category slug pattern already documented in the schema. The description only restates that the category filter is optional and points to mrr_stats, adding little beyond the structured field text.

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?

States a specific verb and resource ('List startups on the ShowMRR public leaderboard ranked by monthly recurring revenue'), plus the data source (showmrr.com). An agent can distinguish this from mrr_search, mrr_stats, and mrr_startup without opening any schema.

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?

Explicitly routes the agent to mrr_stats to discover categories before filtering, and notes the category filter is optional. It does not state when to prefer this over mrr_search (e.g., free-text search vs. ranked listing), leaving one sibling relationship implied.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description is free to add real context: it discloses that the query leaves the system for showmrr.com and that results carry a verification flag. The key interpretive caveat — no match means unlisted, not false — is exactly the kind of behavioral nuance annotations cannot convey.

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 sentences, each doing distinct work: what it does, when to reach for it, and how to read a negative result. The most decision-relevant caveat is placed last and unburied.

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 output schema, the description usefully tells the agent that returned figures carry verified/unverified status, which is the main thing needed to interpret results. It could still say more about result volume or match granularity (exact vs. fuzzy), leaving a small gap.

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% and the single query parameter is already documented with length and character constraints. The description restates "startup name or keyword" without adding syntax, normalization, or matching-behavior detail, so it meets but does not exceed the baseline.

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?

States a specific verb and resource ("Search ShowMRR by startup name or keyword") and scopes it to the external site. An agent can distinguish it from mrr_startup and mrr_leaderboard without opening either schema, since this one is a free-text search rather than a profile or ranking lookup.

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?

Gives a clear trigger: use it to verify a revenue number claimed by a founder or document. It does not explicitly name when to prefer a sibling such as mrr_startup for a known company, so it falls short of full when/when-not routing.

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 openWorldHint, and the description goes beyond them by disclosing the shape of the response (MRR in cents plus currency, verification flag, revenue-as-of date, source page for unclaimed listings) and a data-integrity rule about never presenting 'NOT verified' figures as verified revenue. It does not say what happens on an unknown slug or when the upstream site is unavailable, which is the remaining gap.

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 sentences, front-loaded with the identity and data source, then the return fields, then the sibling routing and the safety caveat. No sentence is redundant with another.

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 output schema, the description carries the burden of explaining return values and does so field by field, including provenance for unclaimed listings. Combined with annotations that cover the safety profile and a fully documented single parameter, an agent has everything needed to call it 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 single parameter idOrSlug is already documented with a pattern and an example ("ghost"). The description's "by numeric id or slug" restates the schema rather than adding new format or resolution-order detail, so the baseline 3 applies.

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 gives a specific verb and resource ("Fetch one ShowMRR startup by numeric id or slug") and names the upstream data source (showmrr.com), which distinguishes it from mrr_search and mrr_leaderboard, whose scopes are searching and listing respectively. An agent can tell this is a single-record lookup without opening the schema.

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 states an explicit usage condition and routing: "Use it to check a specific company after mrr_search finds its slug," which ties the call to a prerequisite sibling tool. It does not state when not to use it (e.g. use mrr_leaderboard or mrr_stats for aggregate views), so the guidance is clear but not exhaustive.

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, non-destructive behavior, so the bar is lower. The description adds genuinely new context: the data source (queries showmrr.com) and the data-quality caveat that totals include unverified figures, which materially affects interpretation. It does not mention freshness or rate limits.

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, both earning their place: the first defines the payload, the second routes usage. The caveat about unverified figures is placed last as a qualifier rather than buried.

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?

There is no output schema, but the description compensates by naming the returned fields and the caveat on totals. Slightly incomplete on return shape (e.g. how per-category totals are keyed) and on data recency, but sufficient for an agent to call it 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 tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. No misleading parameter claims are made.

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?

States a specific verb (aggregate) and resource (ShowMRR numbers) and enumerates the exact outputs: listing counts, verified count, total listed MRR, per-category totals. This clearly separates it from mrr_leaderboard, mrr_search and mrr_startup, which work on individual entries rather than aggregates.

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?

Gives two concrete trigger conditions: fetching valid category slugs before calling mrr_leaderboard, and gauging dataset size before drawing conclusions. It doesn't state explicit exclusions or say when to prefer a sibling instead, so it stops short of full routing 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 already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), but the description adds material context beyond them: the target is sent to a third-party host (seobolt.app), the anonymous rate limit of roughly 3-10 calls per 5 minutes per IP, and the exact response shape (verdict, pass/warn/fail counts, per-check detail with fixes).

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?

Front-loaded with the one-sentence purpose, then input, return, rate limit, and the checker catalogue. The catalogue is long but each line disambiguates an enum value, so it earns its space; the structure could be tightened but nothing is truly wasteful.

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 multi-mode tool with four parameters and no output schema, the description covers what to pass, which mode wants which target form, what comes back, and how failures behave. An agent has everything needed to pick a checker and call it 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 coverage is 100%, so the baseline is 3; the description earns extra by mapping each `tool` enum value to whether it expects a domain or a page URL, which the enum itself does not state. It does not repeat the coercion rules for `target` or the `bots`/`paths` constraints, which live in 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?

States a specific verb and resource ('Run ONE focused SEOBolt checker against a public domain or page') and enumerates the twelve checkers with one-line scopes. It also distinguishes itself from the sibling seo_free_audit by positioning itself as the narrow, single-area follow-up rather than the broad audit.

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?

Gives explicit selection rules: 'Use after seo_free_audit points at an area, or when the user asks about one specific thing'. Each checker entry carries its own domain-vs-URL applicability, and the rate-limit sentence tells the agent exactly what to do on failure ('stop and tell the user; do not loop').

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 readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description does add real value beyond them: it discloses that the domain is sent to a third party (seobolt.app) and gives a concrete rate limit (~5 audits per 5 minutes per IP) plus failure-handling instructions. That is meaningful added context, though it omits anything about latency or what an error response looks like.

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 sentences, each carrying distinct payload: purpose, return shape, and usage/rate-limit. The core action is front-loaded and no sentence is redundant.

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?

No output schema exists, and the description compensates by naming the return contents (overall score, seo and llm sub-scores, prioritized recommendations with fix text). Combined with the external-service disclosure and rate-limit rule, an agent has everything needed to call it correctly and handle failure.

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?

With a single parameter at 100% schema description coverage, the schema already explains that a URL is reduced to its host. The description only restates 'public domain' and adds no format, normalization, or validation detail beyond the schema, so baseline 3 applies.

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?

States a specific verb and resource ('Run SEOBolt's free anonymous audit for a public domain') and immediately contrasts scope with the sibling: broad overview here, drill down with seo_check. An agent can distinguish it from seo_check without opening either schema.

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?

Explicit ordering guidance ('Use it first ... then drill down with seo_check') names the alternative and the condition that selects it. It also states the rate-limit condition and the required behavior on failure ('stop and tell the user instead of retrying'), leaving nothing to inference.

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