olcum

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

Beyond the readOnly/openWorld annotations, the description adds genuinely useful behavior: no authentication required, only the public home page is fetched, and robots.txt is respected. It also discloses that duplicate tags and redirect parameter preservation (UTM, gclid, fbclid, ttclid, oppref) are examined, which annotations alone would not 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?

The content is front-loaded with the checklist of inspected items, which is effective, but the full bilingual duplication roughly doubles length and is not strictly necessary since the title already signals the Turkish audience.

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 three-parameter, no-output-schema audit tool, the description covers inputs only via 'url' and the check categories imply what findings come back, but it never states the shape of the result or what happens on failures (unreachable site, blocked robots.txt). Completeness is adequate but leaves meaningful gaps.

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 0%, so the description must carry parameter meaning, yet it never mentions 'country' or 'language' and only implies 'url'. Two of three parameters are left entirely unexplained in both schema and description, and the default language of 'tr' is never connected to the bilingual output.

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 names a concrete verb and resource ('checks an e-commerce site's ad measurement') and enumerates exactly which tags and behaviors are inspected, so an agent can predict the scope. It does not, however, distinguish itself from the sibling 'diagnose_ad_report', which remains a borderline ambiguity.

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: it makes clear this is a public-facing, no-sign-in audit of a home page, which implicitly excludes post-login or campaign-performance analysis. There is no explicit when-to-use/when-not guidance and the sibling tool is never referenced as an alternative.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral facts: no authentication required, the report is not stored, and it is processed only for this request. It also discloses what the analysis returns, which the annotations do not cover.

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?

Content is front-loaded well: purpose first, then input-handling rules and privacy notes. However, the entire description is duplicated in Turkish and English, roughly doubling length without adding new information for an agent, which is redundant rather than concise.

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 correctly takes on the burden of describing what the diagnosis returns, and it does so adequately. The gap is the input side: two optional parameters are entirely unexplained, and there is no mention of report size limits or malformed-CSV behavior for a tool whose whole job is parsing a free-form text blob.

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 0%, so the description must carry parameter meaning, and it only explains the required `report_text` (raw CSV, no reformatting, no dropped columns). The `platform` and `platform`/`language` parameters are never mentioned — neither their purpose nor their defaults — leaving two of three parameters undocumented in both schema and description.

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: it diagnoses a campaign report exported from one of four named ad platforms, and enumerates the concrete findings it returns (spend without sales/conversions, the campaign to check first and why, last 7 days' trend). An agent can distinguish this clearly from the only sibling, check_site_measurement, which concerns site measurement rather than report diagnosis.

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 clear operational context: use it on a report exported from an ad panel, pass it exactly as exported as raw CSV text, don't convert to a table or drop columns, and no sign-in is needed. It does not, however, state when *not* to use it or compare it against the sibling check_site_measurement tool, so routing is implied rather than explicit.

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