NetActuate

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

Annotations already declare readOnly/non-destructive/non-open-world, and the description adds substantial extra context: distances come from city centroids and are approximate guidance, not latency guarantees, and unrecognized places are reported rather than silently dropped. These caveats go well beyond the structured safety hints.

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?

Front-loads the core purpose in the first clause, then layers examples and caveats. Every sentence carries weight, though the final sentence about the built-in city list and coordinate fallback is dense and could be tightened.

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?

No output schema exists, yet the description still outlines the return shape ('a site summary with distanceKm, nearest first'). Combined with the accuracy caveat and coordinate fallback, an agent has everything needed to call and interpret results.

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%, so the baseline is 3, but the description adds real semantic value: it specifies that 'location' should be the target market/end-user place rather than the asker's location, and that lat/long is the fallback when a name is unrecognized. That clarifies intent beyond the schema's field-level docs.

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: ranks NetActuate data centers by great-circle distance from a named place. This is clearly distinct from siblings like list_data_centers (enumerate) or get_data_center (fetch one), so an agent can route without opening either 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 concrete when-to-use triggers ('what is your closest location to Lagos') and a genuine when-not nuance about passing the place the question is about rather than where the asker is. It stops short of naming an explicit alternative sibling for the non-geo case, so it is strong context without full alternative routing.

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 cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), but the description goes further by spelling out both invocation behaviours: no argument returns every published certification plus per-certification site counts, and a certification argument lists matching sites with a publishedAs field as evidence. It also discloses name normalisation, which is a real behavioural trait an agent could otherwise be surprised by.

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 lead sentence front-loads the concrete answer the tool provides, and each of the four sentences carries distinct information (return shape, filtered return shape, normalisation, routing to the sibling). It is dense but nothing is padding; a slightly tighter phrasing of the normalisation sentence would be the only trim.

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 carries the return-value burden and does so for both the unfiltered and filtered cases. Combined with annotations covering safety and a fully documented single parameter, an agent has everything needed to select and invoke the tool 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?

Schema coverage is 100%, including the multi-value 'and'/'or' semantics, so the baseline is 3. The description adds value beyond the schema by explaining why matching works on normalised names (the website writes some standards several ways), which tells the agent that loose/variant certification strings will still match.

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 question the tool answers ('which NetActuate locations are SOC 2 / HIPAA / PCI-DSS / ISO 27001 certified') across a defined scope (the whole footprint). It explicitly distinguishes itself from list_data_centers' certification filter, so an agent can separate the two without opening either 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?

It gives both the when ('Use it for regulated-workload placement') and the alternative with its selecting condition ('to combine a certification with a region or country, use list_data_centers' certification filter instead'). No prerequisite or exclusion is left to inference.

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 read (readOnlyHint=true, destructiveHint=false), and the description goes well beyond them: it discloses the '(extension)' second-facility convention, the otherSitesInCity field on city-name lookups, candidate-return behavior for partial names instead of guessing, and the caveat that coordinates are city-centre rather than facility address. That is substantive behavioral context an agent could not infer from the 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?

Front-loaded with the return payload, then usage routing, then edge cases. Every sentence carries distinct information; the enumeration of returned fields is dense but justified given there is no output schema.

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 compensates by naming the content categories returned and the special fields (Looking Glass node id, otherSitesInCity). Combined with the 100%-covered input schema and safety annotations, an agent has everything needed to call it 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%, so the baseline is 3, but the description adds meaning the schema does not: how a bare city name is resolved (primary site in full, others named in otherSitesInCity), and that a partial match yields candidates rather than an arbitrary pick. These are real semantics for the single 'location' parameter beyond the slug/city format already documented in 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?

Opens with a specific verb+resource and enumerates exactly what is returned (building specs, compliance, security, connectivity, power, Looking Glass node id, FAQs, URL). It is immediately distinguishable from list_data_centers and find_nearest_data_centers, which are named as the discovery alternatives.

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 states the trigger condition ('Use it once the site is known') and routes to the correct siblings for discovery ('to find sites, use list_data_centers or find_nearest_data_centers'). It also documents disambiguation behavior for ambiguous input, which is a usage concern rather than a schema one.

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, but the description adds genuinely non-obvious behavior: long pages are truncated with a note stating how much is shown, ambiguous names return up to ten candidates instead of guessing, and the response includes summary, headings, body copy, FAQs and the canonical URL.

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?

Five sentences, each carrying distinct information: scope, contents, usage trigger, accepted inputs, disambiguation, truncation, and the sibling exclusion. The usage trigger is front-loaded right after the contents, and nothing is repeated verbatim from the schema.

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?

No output schema exists, so the description takes on the burden of describing the return shape (summary, headings, body, FAQs, URL) and does so, plus it explains truncation and multi-candidate responses. Nothing an agent needs to call or interpret this tool 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% and the single parameter's accepted forms (slug, URL, page name) are already documented in the schema with examples. The description restates the same accepted inputs and adds only the multi-match behavior, which is response behavior rather than 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?

States a specific verb (returns full published text) plus the exact resource scope, enumerating the page types it covers (product, solution, category, case study, region, internet exchange, company). It also explicitly carves out data centers, so an agent can distinguish it from get_data_center at a glance.

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 trigger ('when a question needs more than search_netactuate's one-line summaries') with concrete examples, and names the alternative tool for the excluded case ('For a data center use get_data_center'). Both when-to-use and when-not-to-use are covered.

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 read-only, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful operational context beyond that: no filter returns every site, an unrecognised region/country is surfaced in a note rather than an error, and an empty list means no published match — which prevents the agent from misreading a filtered miss as a failure.

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, each earning its place: purpose+scope, return fields, usage examples, sibling routing, and the empty-result edge case. The scoping and routing information is front-loaded rather than buried.

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 compensates by listing the returned fields (slug, name, city, country, region, certifications, URL). Combined with the empty-list semantics and sibling routing, an agent has everything needed to select and call this tool 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?

Schema description coverage is 100% and each parameter already documents its own accepted values, synonyms ('APAC', 'EMEA', 'LATAM') and the 'and'/'or' certification semantics. The description only restates that filters can be mixed, adding no syntax or format detail beyond the schema, 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?

Opens with a specific verb and resource ('Lists NetActuate's data centers (points of presence)') and immediately states the filter dimensions and the no-filter default. It also enumerates the returned fields, so an agent knows exactly what this tool produces versus siblings.

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 example queries ('where does NetActuate have presence', 'anything in Asia') and routes three distinct alternative needs to get_data_center, find_nearest_data_centers and get_compliance_coverage by name. This is explicit when-to-use and when-to-use-something-else 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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description goes further by disclosing default behavior ('with no query it returns every exchange NetActuate publishes a page for') and enumerating the returned fields (slug, name, description, page's opening paragraph, and URL), which goes beyond what the annotations provide.

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?

Front-loaded with the core purpose, then default behavior, then usage examples, then sibling routing. Four sentences, each carrying distinct information with no redundancy or filler.

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?

No output schema exists, yet the description describes the shape of each result (slug, name, description, opening paragraph, URL), so the agent knows what comes back. Combined with the query behavior and sibling pointers, nothing needed to call this correctly 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 coverage is 100%, so the baseline is 3. The description adds real semantics on top: no argument means return everything, and the note that exchange pages name cities rather than regions tells the agent how to phrase the query value — information the schema's own description does not supply.

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 precise verb+resource (lists internet exchanges where NetActuate offers colocation, bare metal, VMs or remote peering) with concrete examples (AMS-IX, DE-CIX, LINX). It explicitly distinguishes itself from siblings by naming get_netactuate_page for full pages and list_data_centers for the facilities themselves, so an agent can route correctly without opening other schemas.

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 explicit when-to-use scenarios (peering/interconnection questions such as 'does NetActuate peer at DE-CIX') and names the two alternative tools with the conditions that select them. It even adds a filtering caveat — exchange pages name cities, not regions — which steers query construction.

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 safe-read profile is covered. The description adds real context beyond them: it clarifies that the call takes no arguments, scopes exactly what the result set includes and excludes, and points to the tool that retrieves full text. It does not discuss pagination or result size, which is a minor gap.

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 return contents are front-loaded in the first sentence, followed by the no-argument note and the two exclusion/routing lines. It is dense and mostly waste-free, though the long enumerated parenthetical makes the opening sentence harder to scan.

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 carries the burden of explaining the return shape and does so thoroughly (slug, name, one-line description, URL). Combined with the exclusion list and the pointer to get_netactuate_page for full text, 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?

There are zero parameters, so the baseline is 4. The description reinforces this with 'Takes no arguments,' removing any ambiguity about whether filters are accepted.

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 NetActuate's product categories ... and solution pages') and enumerates the actual contents, so an agent knows exactly what comes back. It also distinguishes itself from search_netactuate and get_netactuate_page by naming the content those tools cover instead.

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 use case ('Use to answer what does NetActuate actually sell'), an explicit exclusion (individual product pages and pricing pages are not listed here), and routes the agent to the correct alternatives (search_netactuate, get_netactuate_page). When-to-use, when-not-to-use, and alternatives are all present.

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/openWorld=false/destructive=false, and the description adds real behavioral detail beyond them: conjunctive matching ('every word of the query must appear'), relevance ranking within content type, truncation semantics via matchCounts, and one-line result granularity. It stops short of edge behavior such as zero-match handling or index freshness.

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?

Front-loads the core action and corpus, then matching rules, then usage, then result format — a sensible order. The long mid-sentence enumeration of content types is informative but heavier than needed; otherwise no wasted sentences.

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 carries the return-format burden and does so: one-line summaries, matchCounts, and the slug needed to call get_netactuate_page. Slightly thin on exact result fields and behavior on empty result sets, but sufficient for correct invocation.

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%, so both query and limit are already documented (including AND semantics and the 1–50 per-type range). The description restates the conjunctive matching rule and explains that limit cuts per content type with matchCounts recovering the total, which is marginal added meaning rather than new parameter syntax.

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 ('keyword search across NetActuate's published pages') and enumerates the corpus covered (data centers, IXs, solutions, product pages, pricing, case studies, news, FAQ answers). This is clearly distinguishable from siblings like list_data_centers or get_netactuate_page, which are named or implied as different scopes.

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 selection condition — 'Use this when no more specific tool fits, for product and pricing questions, or to find which case study covers a use case' — and routes the follow-up step to get_netactuate_page by slug. When-to-use, fallback role, and the alternative drill-down tool are all stated.

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