SEO Records Corrector

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

Annotations only declare readOnly/idempotent/openWorld; the description adds substantive behavior: the page is read, corrected in memory and forgotten (nothing is persisted), the tool is free, and it returns the correction value, its source, and the exact HTML tag to add or replace. It also proactively names the limitations — issues left to the author such as missing h1 and vague link texts — which an agent could not learn from the 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?

Purpose is front-loaded and every clause adds information (the corrections returned, the return shape, the non-persistence, the author-owned issues, docs link). It is dense to the point of being a run-on paragraph, but there is little wasted 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?

With no output schema, the description must describe the return payload, and it does: corrections with value, source, and target HTML tag, plus a before/after Google snippet and a list of unfixed issues. Nothing essential for correct invocation is missing.

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?

There is a single url parameter with 100% schema description coverage including a format example, so the schema already carries the semantics. The description adds no extra syntax or constraint detail (e.g. accepted schemes, trailing slash handling) beyond what the schema provides, so the baseline of 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 ('Runs the SEO Records correction engine ... on a public page and returns every correction it would apply'), which is far more than a restatement of the name. It enumerates exactly which fields are analyzed (title, meta description, canonical, hreflang, OG/Twitter, JSON-LD, alt texts, robots). It does not, however, distinguish itself from the sibling get_automatic_fix_offer, leaving the agent to infer the boundary.

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: calling it on a 'public page' to preview corrections, plus the note that it is free and non-destructive. There is no explicit when-to-use versus get_automatic_fix_offer, and no stated prerequisites or exclusions beyond issues that touch visible content.

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 safety is covered. The description adds genuinely useful behavioral content beyond that: the response includes product descriptions, prices and secure Stripe payment links, which tells the agent what it will get back without an output schema.

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?

One front-loaded sentence that is readable, but it is padded with marketing content — the same €199/year price repeated twice and a docs URL — that is not needed to select or invoke the tool correctly.

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 trivial one-optional-param read tool with annotations covering safety, the description is adequate, but it lacks any indication of the shape of the returned offer list (one product vs many, ordering, currency) which matters since there is 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?

Schema description coverage is 100% and the single language enum parameter is fully documented in the schema (default en). The description never mentions the language parameter, so it adds no meaning beyond what the schema already provides; 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: returns SEO Records products that apply corrections automatically, listing what each offering does, its price, and a payment link. An agent can tell this is an offer/commerce lookup rather than the sibling fix_page_seo action, though fix_page_seo is never named for contrast.

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 statement of when to call this versus fix_page_seo, and no prerequisites or exclusions. The commercial framing implies the agent should use it when a user asks about automated fixes, but that inference is left entirely to the reader.

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