Machine Relations Index

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false), so the bar is lower. The description still adds real behavioral content: it discloses the evidence-state vocabulary returned per question type ('published with rates, collecting, or not collectable'), which is not derivable from any structured field.

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 stating the return payload, with the enumeration folded into a parenthetical rather than expanded into prose. Dense but every clause carries content; only minor cost is the long inline list.

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 and only one param, the description does the heavy lifting by describing the return shape: the set of question shapes and the three evidence states. It stops short of explaining what a rate looks like or any pagination, but it is sufficient for an agent to call this correctly and interpret the result.

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% with a single required 'category' key, and the schema already supplies the format hint and the cross-reference to mri_list_categories. The description adds no further parameter meaning, 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?

Specific verb ('Return') plus resource ('one category's question shapes') and an enumerated list of the shape types it covers (best tools, comparisons, top lists, etc.). It is clear what the tool yields, though the description itself never names the sibling tools it is distinct from (mri_list_categories / mri_get_domain), so differentiation is left to the 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?

No explicit when-to-use or when-not-to-use statement. The sequencing is only implied by the parameter's schema note ('Category key from mri_list_categories'), which tells the agent this follows a listing call, but the description offers no exclusions or alternatives.

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 this a read-only, idempotent, closed-world operation, so the safety profile is covered. The description adds genuinely useful behavioral context that annotations cannot: the metric semantics (citation rate as share of monitored answer runs, rank, percentile) and the full source-role taxonomy, which is expanded beyond the schema's example list.

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 core purpose before the usage examples, and no filler. The first sentence is dense with enumerated fields but each clause earns its place by describing what is returned.

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 does the work of describing return values (domains, citation rate, rank, percentile, source role), which is exactly what an agent needs to read results. Remaining gaps are freshness/date range of the monitored runs and how limit/offset pagination behaves across the ranked list.

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 60%, and the description compensates by enumerating source_role values that the schema only hints at (adding academic/government, market database and wire distribution). question_shape and category meanings are aligned with the schema; limit/offset are left to the schema, which is acceptable since they carry defaults.

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 first sentence names a specific resource (ranked source domains cited by AI answer engines) scoped to one category and question shape, and enumerates the returned measures. This is clearly distinct from siblings like mri_get_category, mri_get_domain and mri_list_categories, which cover categories and single domains rather than cited-source rankings.

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?

The second sentence gives two concrete use cases ('which publications does ChatGPT or Perplexity cite for <category>' and 'where should a brand earn coverage to be cited'), which tells the agent when to reach for this tool. It stops short of naming alternatives or stating when NOT to use it (e.g., for a single domain, use mri_get_domain).

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, destructiveHint=false and a closed world, so the safety profile is covered. The description adds real value by disclosing what the result contains (confidence tier, overall rank, rank within source role, per-category rates), which is the only place that information exists since there is no 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?

Two sentences: the first front-loads the scope and the returned fields, the second supplies the use-case triggers. No filler, though the enumeration of output fields is fairly dense.

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, no output schema, and annotations covering safety, the description supplies the needed return-value detail and intent framing. Pagination and error/empty-result behavior are not covered, which is the only remaining gap for a read-only lookup.

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 'domain' parameter already explains 'a domain (techcrunch.com) or any URL on it.' The description restates the same 'domain or URL' flexibility without adding syntax, normalization, or error behavior, 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 ('return how often AI answer engines cite it') scoped to a single domain or URL, and enumerates the returned metrics (citation rate, engines, confidence tier, ranks, segment rates). It differentiates implicitly from the list-oriented siblings by being per-domain, but never names an alternative, so it falls 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?

Gives concrete triggering questions — 'does ChatGPT/Perplexity cite <site>' and 'how authoritative is <publication> as an AI source' — which clearly frames when to reach for it. It offers no exclusions or explicit pointers to mri_get_cited_sources/mri_get_category for the aggregate case, so it stops short of a 5.

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 establish readOnly, idempotent and closed-world safety, so the description only needs to add content context — and it does, specifying that results include question shapes with published citation rates plus the source-role vocabulary. It stops short of saying whether results are cached or stable across releases.

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 tight sentences, front-loaded with the payload description and ending on the actionable instruction. Every clause 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 no parameters, no output schema, and full annotation coverage, the description supplies enough to call the tool and interpret its use. It could note the shape of a returned key (string vs object), but nothing essential 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?

Zero parameters, so per the rubric the baseline is 4. The description appropriately spends its words on return content rather than inventing parameter semantics that do not exist.

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 ('List every Machine Relations Index category') and enumerates example values, so the agent knows exactly what comes back. It does not explicitly contrast with sibling mri_get_category, but the domain is narrow and self-evident.

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?

'Call this first to get a valid category key' gives clear ordering/precondition guidance that routes the agent before it attempts mri_get_category. No when-not guidance, but for a discovery endpoint none is really needed.

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