Testez votre tracking

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description meaningfully extends them: no Google/Meta account access or key required (works purely from the public URL), the tool does not execute the site, and it deliberately excludes purchase-event and data-reception verification. It also discloses the report language (French) and that the score is indicative, which are real behavioral traits not captured by 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 is substantive (scope, exclusions, outputs, coverage, attribution, doc link). The main cost is the near-total duplication of the same content in the English restatement, which inflates length without adding information, though it aids bilingual discoverability.

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 a rich annotation set, a full output schema, and 100% schema coverage, the description still adds the auth model (none needed), the execution boundary, and the excluded checks — everything an agent needs to decide and call correctly. Nothing material 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?

Schema description coverage is 100%, including the meaning of both enum values for 'detail', so the schema carries the parameter burden. The description mentions the public URL as the input source and 'la page demandée', but adds no syntax, format, or enum nuance beyond what the schema already documents, 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?

States a specific verb and resource: a read-only audit of a site's observable marketing tracking config, sourced from the requested page and public GTM containers. Names the concrete output (score /100, risks, fixes, verification limits) and the covered stack (GTM, GA4, Google Ads, Meta, TikTok, Pinterest, cookie banner, Consent Mode v2, server-side). An agent can tell exactly what this does even without siblings to contrast against.

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 gives the trigger ('Cas d'usage : test, audit ou vérification du tracking d'un site précis, à la demande de l'utilisateur') and clear scope boundaries (no account access, does not execute the site, does not verify purchase events or platform data receipt). Lacks a formal when-not/alternative routing statement, but with no sibling tools that gap is immaterial.

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