index

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still earns credit by disclosing the return structure (per-axis breakdown, date, scoring scale) and, notably, that it also returns 'what the measurement does not say' and only exposes published measurements — real behavioral context beyond 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?

Two sentences, front-loaded with the primary return value and then enumerating the secondary payloads; almost no waste. The phrase 'what the measurement does not say' is slightly opaque but does useful work.

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 fully compensates by enumerating what comes back (score, per-axis breakdown, date, scale, caveats), and the single parameter is documented in the schema. Combined with annotations that already cover safety, an agent has everything needed to call this 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?

One parameter with 100% schema description coverage ('a host name, e.g. renault.fr'), so the schema carries the semantics and baseline 3 applies. The description only refers to 'a domain' generically and adds no format or resolution detail beyond 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+resource ('Returns the published Agent Readiness Score of a domain') and defines what the score measures (what an AI assistant can read without JavaScript), which is genuinely clarifying. It does not, however, differentiate itself from the sibling tools it sits beside (ce_qui_manque, devis, secteur, secteurs_disponibles), which is the only thing keeping it from a 5.

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?

There is no explicit statement of when to call this tool versus a sibling, nor any exclusions. The closest thing is the ownership caveat 'Only published measurements are returned; see the server instructions for who decides,' which is a governance note rather than usage 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is fully covered by structured data. The description adds that the response includes a measured finding per axis plus 'buying questions no page can ever answer', which hints at return content but is vague about structure or scope.

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 front-loaded sentence that states the resource first and layers on the return contents; it is efficient with no filler, though the nested clauses make it dense to parse.

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 carry the return semantics, and it only partly does: it names three categories of output without explaining what an 'axis' is or how to read the score. For a one-parameter read tool this is adequate but leaves the agent guessing at interpretation.

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?

Only one parameter (domaine) and schema coverage is 100%, so the schema already carries the meaning ('a host name, e.g. renault.fr'). The description adds no syntax or constraint detail beyond that, which matches the baseline-3 case.

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 verb 'Returns' and the object 'weakest axes of a published domain' give a rough sense of a diagnostic/audit tool, but 'axes' and 'published domain' are unexplained jargon that a new agent must guess at. It does not differentiate itself from the sibling 'agent_readiness', which sounds like a closely related readiness/audit concept.

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?

There is no when-to-use guidance, no prerequisites, and no mention of the alternatives among siblings (agent_readiness, secteur, secteurs_disponibles). The agent is left to infer the trigger condition from the name alone.

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, non-destructive and closed-world, so the safety profile is covered. The description adds real behavior beyond that: the answer is returned line by line with source and date, and a missing quantity is never guessed but reported back.

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?

Four sentences that are front-loaded with the core action and scope, then the exclusion and the example. Dense but every sentence carries distinct information with no restatement of the title.

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 appropriately explains the return (line-by-line calculation with source and date) and the degenerate case (missing quantity). Combined with annotations, an agent has what it needs to call and interpret the tool.

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 already 100%, so the baseline is 3, but the description adds meaning: the 'question' must carry quantities/options/period and is answered in any language, plus a worked example (entreprise = example.com, question = 'how much for 800 units in 6 variants per month?'). This concretely shows the expected input shape.

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 concrete verb (computes) and resource (an exact price for a specific case) and pins the source (the company's own deposited price list), returning it line by line. It scopes itself away from the published Index and rankings, so the agent can place it relative to the domain's other tools without opening a 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 an explicit eligibility condition ('Only companies that have deposited a price list are covered... Isoligne clients') and a when-not ('unrelated to the published Index and rankings'). It does not name the actual sibling tools or say when to prefer them, but the applicability boundary is clear.

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 a safe, idempotent, closed-world read. The description goes well beyond them, disclosing that Isoligne decides publication after notifying each company, that client status affects neither inclusion nor order, and that scores within 5 points are not separated. It omits only the shape of what is returned.

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?

Four tight sentences with the output behavior front-loaded and no filler. The Isoligne sentence is arguably marginal but it carries real inclusion semantics, so it earns its place.

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 one required parameter and no output schema, the description must carry the return semantics, and it does explain grouping by level and score-based ordering with tie handling. What is missing is the actual structure of a returned entry (site fields, score field), which the agent must still infer.

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 parameter with 100% schema description coverage, and the schema already explains it is a sector key from secteurs_disponibles with an example. The description adds nothing about the parameter, 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 states a specific verb and resource: it returns a sector's published sites, grouped by level and ordered by score. It also pins the scope (published sites only, not the whole market). It does not name or distinguish itself from siblings like secteurs_disponibles, so it stops short of a 5.

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 ranking covers published sites only, which tells the agent this is not a market-wide listing. There is no explicit when-to-use or when-not-to-use guidance, and no mention of the sibling tool that supplies the sector key.

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, non-destructive and closed-world, so the safety profile needs no restating. The description adds one genuinely useful behavioral fact — that unpopulated sectors are excluded — but says nothing about the shape or ordering of results, and there is no output schema to fall back on.

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 front-loaded sentence with no filler, hedging, or repetition of the title. Every word earns its place.

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 zero-param, read-only, closed-world listing tool the annotations carry most of the burden, and the filter rule is stated. However, with no output schema, the description leaves the return shape unspecified (labels vs. codes, whether counts are included), which an agent would want to know before calling.

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 there is no parameter semantics to document; the baseline of 4 applies. The description correctly avoids inventing or implying any inputs.

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 ('Lists the sectors') plus a meaningful scope qualifier ('with at least one published company'), which sets it apart from a bare sector lookup like the sibling 'secteur'. It doesn't explicitly name or contrast with siblings, so it stops short of a 5.

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 only implied: an agent can infer this is the enumeration call for sectors, but there is no statement of when to prefer it over 'secteur' or 'ce_qui_manque', and no exclusions or prerequisites. Adequate but with a clear gap.

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