GEO SEO Records

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description goes beyond that by disclosing a paid gating requirement (€9.90/24h or €29/month), the weighted output taxonomy (blocking/important/to decide), and the six assessment axes. It omits failure behavior, rate limits, and whether the pass is validated per call.

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 verb and resource, then the output shape, then the paywall, then docs. The six-part parenthetical is dense but each clause conveys distinct assessment scope. No filler sentences, though the pricing detail could be compressed.

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 must convey what comes back, and it does: weighted gaps across six named parts. It also discloses the access-pass requirement and points to docs. Remaining gap is error/precondition handling for non-public pages and whether the pass is consumed per 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 coverage is 100%, so baseline is 3. The description earns an extra point by explaining where access_key comes from (shown after buying the 24-hour pass or subscription) and asserting it is required, which is useful because the schema's required array lists only url. That required-flag mismatch would otherwise confuse an agent.

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: runs the GEO SEO Records engine on a public page and returns weighted gaps. The six-part enumeration (robots.txt door, llms.txt map, answer, citable, publisher identity, structure) makes the scope concrete. It never names or routes against siblings like draft_llms_txt or open_robots_txt_to_ai, so it stops short of full 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?

Usage is implied: audit one public page's AI-readiness. The description adds a prerequisite (buying the access pass) but gives no explicit when-to-use versus get_geo_offer, draft_llms_txt, or open_robots_txt_to_ai, and no when-not-to-use conditions such as private or non-public pages.

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, openWorldHint and idempotentHint, so the safety profile is covered; the description still adds real substance by disclosing the read sources (home page, sitemap), the fact that an existing llms.txt is reviewed for unverifiable claims, and that the result is a draft rather than a live publish. The paid access pass requirement, with prices, is important behavioral context an agent would otherwise not know. It stops short of describing the response shape or any rate/volume 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?

The primary action is front-loaded in the first clause, and the remaining sentences cover inputs, review behavior, output location and the access requirement. The second clause is dense but every element is informational; only the docs link and price detail are marginal.

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, so the description must convey the return: it does, saying the draft is ready to edit and publish at /llms.txt. Combined with the input source disclosure and the access-pass prerequisite, an agent has enough to call it correctly; the only gap is what the draft response actually looks like structurally.

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 both parameters carry descriptions, so the baseline would be 3. The description goes slightly beyond by explaining what the url is used for (facts read from the site) and by adding the price and the docs URL for obtaining access_key, which the schema only alludes to as 'shown after buying'.

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 opens with a specific verb and resource — 'Builds an llms.txt for a website' — and then enumerates the exact inputs (home-page name/description, sitemap pages with titles and meta descriptions, grouped by section) plus the review of any existing file. That is far more concrete than a restatement of the title. However, it never contrasts itself with actual siblings such as check_ai_readiness or open_robots_txt_to_ai, so an agent must infer that this is the drafting action rather than the diagnostic one.

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?

Usage is implied rather than stated: the tool produces a draft 'ready to edit and publish at /llms.txt', which signals the situation it is for, and the access-pass sentence establishes a prerequisite. But there is no explicit 'use this when…', no exclusion of cases where the draft should not be generated, and no routing to the sibling tools.

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=false, so the safety profile is covered. The description adds commercial context (pricing, Stripe payment links) but says nothing about response format, currency handling, or whether the offer is static. 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?

A single sentence that is front-loaded with the verb and resource, which is good. However, a large portion is promotional jargon ('door, map, answer, publisher', 'assistant reads certified by IP range') that does little to help an agent decide to invoke the tool.

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 is simple (one optional param, no output schema), and the description does convey that the response includes module details, prices, and payment links. But with no output schema, the description could more precisely describe the returned structure rather than relying on marketing framing.

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 'language' parameter is fully documented in the schema with an enum. The description adds nothing about the language parameter, so the baseline 3 for high-coverage schemas 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+resource ('Returns the GEO SEO Records module') and clarifies the output ('with prices and secure Stripe payment links'). The topic is clearly distinct from siblings (readiness checks, llms.txt, robots.txt), though the description never names them explicitly and the marketing copy ('door, map, answer, publisher') muddies the core function.

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 on when to call this versus the sibling tools. It gives no trigger condition, no exclusions, and no indication of when an agent should fetch the offer rather than run check_ai_readiness or draft_llms_txt.

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 the description adds genuinely non-obvious context: the €9.90/€29 payment gate, the required access key, and that the corrected file is returned 'ready to paste' rather than applied. It is consistent with readOnlyHint since nothing is written to the site. It stops short of describing the response shape or failure modes (e.g. what happens on an unreachable site).

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?

Purpose is front-loaded in the first clause and the long robot enumeration is functionally necessary for the tool's verdict output. The commercial and docs details are pushed to the end. Slightly dense, but no sentence is filler.

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 return-value explanation and does so: per-robot verdicts plus a paste-ready corrected robots.txt. Missing only edge-case behavior (invalid URL, expired pass), which a tool of this shape would benefit from.

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 both parameters are already documented, making 3 the floor. The description earns extra credit by explaining what the 'access pass' reference in the access_key field actually is and how it is obtained, plus the docs URL.

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+resource ('Reads the site's robots.txt') and describes the output precisely: a per-robot verdict split into live readers vs training harvesters, plus a corrected robots.txt. The enumerated robot list and the 'live vs training' framing make it clearly distinct from siblings like draft_llms_txt or check_ai_readiness.

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 never says when to use this instead of check_ai_readiness or draft_llms_txt, and offers no exclusion conditions. The only conditional content is a prerequisite (paid access pass), which is not the same as usage routing.

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