Tensorust Ontology

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and closed-dataset behavior are covered. The description adds genuinely useful scope constraints (US-only, turbine aircraft only) and previews the returned fields, but says nothing about multiple matches when searching by owner name, result limits, or how the two parameters interact.

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 the lookup key stated before the returned fields, and no filler. The parenthetical alternative mode is slightly compressed but does not obscure the meaning.

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 two-parameter read-only lookup with no output schema, the description is close to sufficient: it defines both inputs, the domain restriction, and the shape of the response. The remaining gap is ambiguity around owner-name searches returning multiple aircraft and any result-size behavior.

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 largely does: n_number is identified as an N-number and owner as a registered owner name, with the parenthetical framing them as alternative lookup modes. It falls short of stating whether the parameters are mutually exclusive or which takes precedence if both are given.

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 specific verb (look up) and a specific resource (US turbine aircraft by N-number or registered owner name), then enumerates the exact fields returned: registered owner, owner-trustee status, model, and FCC radio altimeter rebate category and proposed rebate. This is clearly distinct from siblings like who_owns_home or lookup_organization, which target different entity types.

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: an agent can infer this is the tool for aircraft ownership questions, and the parenthetical shows two lookup modes (N-number vs. owner name). However, there is no explicit when-not guidance, no mention of the sibling tools, and no statement about which mode to prefer or what happens if both or neither parameter is supplied.

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?

Beyond the readOnly/openWorld annotations, the description discloses the data provenance (SEC filings), the fixed as-of date, the sort order, a hard result cap on the free tier, and the exact paid-access mechanics ($0.25 per call over x402 in USDC on Base, or a Tensorust key). That is precisely the billing and coverage context an agent needs before calling and is not derivable from the structured fields.

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 definition of the dataset before the access/pricing terms. Every clause carries information (criteria, date, ordering, free cap, paid fields, price), though the second sentence is dense enough that a reader must parse payment mechanics and return fields in one pass.

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 single-boolean, read-only query tool with no output schema and fully covered params, this covers selection criteria, ordering, result contents, caps and cost. The only gaps are the snapshot's fixed date (no date parameter exists, which could surprise an agent wanting another quarter) and any indication of list size beyond the top-10 cap.

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% and the single parameter already carries a description, so the baseline is 3. The tool description still adds genuine meaning: it enumerates what the paid response contains (every fund's mark, par, prior-quarter mark, filing link) and clarifies that the default non-full behavior is the free top-10 view, which the schema alone does not convey.

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-and-resource outcome: US first-lien loans where two or more BDC managers mark 10+ points apart at a specific as-of date, drawn from SEC filings, ordered widest-gap-first, returning borrower, low/high manager, marks and par. This is specific enough to separate it from the sibling lender_marks 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?

Clear usage context is given via the tiering rule: the default call is free and returns only the top 10, while full=true returns the complete list. What is missing is an explicit statement of when to prefer this over a sibling such as lender_marks (e.g., single-manager marks vs. cross-manager dispersion) or any exclusion condition.

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 cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real context: the source (each Q3 10-Q on EDGAR), the freshness (the day it is filed), the ordering (biggest cut first), and the paywall mechanics (top 10 free, $0.25 via x402/USDC on Base or a Tensorust key). There is a mild tension with openWorldHint=false given the live external EDGAR feed, though the result set is bounded enough that it does not read as a flat contradiction. What it omits is the record shape — fields per cut/holder — which matters for a paid, metered call.

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 earnings-season hook and the cut definition before the pricing clause. The free-vs-paid detail is repeated between description and schema, and the second sentence is dense, but nothing is 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?

With no output schema, the description carries the burden of describing returns and does so reasonably: cuts ranked biggest-first, pending holders flagged as likely next markdowns, and the top-10 free cap implying truncation behavior. A per-record field list or an explicit note that results are current-as-of-latest-filings would close the remaining gap.

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 optional boolean parameter, and its schema description already states the full=true expansion plus the $0.25/x402 pricing and key alternative. The prose restates that tradeoff and adds 'every pending holder,' which is a marginal gain over the schema. With 100% coverage the baseline of 3 is appropriate.

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 precise verb and resource: BDC funds that cut a first-lien loan's mark by 5+ points between Jun 30 and Sep 30 2026, sourced from Q3 10-Qs on EDGAR. That scope is narrow enough to distinguish it from siblings like lender_marks or credit_disagreements without opening any 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 clear situational context — 'Live through earnings season' — and explains the free-versus-follow-up use case via the pending-holder angle, which tells the agent what question this answers. It never explicitly excludes or routes to sibling tools, so it stops short of full when/when-not 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 and openWorldHint=false, so safety is covered; the description goes beyond that by disclosing the pricing model ($0.05/call via x402 USDC on Base), the alternative auth path (Tensorust key), and the difference in return content between free and paid tiers. Missing is what happens on payment failure or whether the x402 terms are returned as an error-like response.

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 dense sentences with the core action front-loaded and no filler. The pricing details are compressed but jargon-heavy (x402, USDC on Base) and partly duplicate the schema's `full` description, which slightly undercuts efficiency.

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 describing returns, and it does so at a useful level: 'card', 'counts and previews', 'every linked object and property'. Combined with the pricing/auth disclosure, an agent has enough to call it correctly; only error and payment-failure behavior is unaddressed.

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 50%, with `id` undocumented in the schema but explained in the description via concrete prefixed examples, which is real added meaning. The `full` explanation largely repeats the schema text, and the cost/auth implications are the genuinely new part.

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 ('Expand') and resource ('ontology id ... into its card') and gives three concrete id-format examples (org:, cg:, rule:), so an agent can recognize valid input. It does not explicitly distinguish itself from sibling lookup_organization or search_organizations, which keeps 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?

It does give a clear when-to-use signal for the `full` flag: omit for free preview, set true for every linked object and property. However, there is no guidance on when to choose this tool over lookup_organization or search_organizations, which is the main ambiguity an agent would face given the sibling set.

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 only declare readOnly and closed-world; the description goes far beyond, disclosing the source (SEC 10-Q filings), the as-of date, the exact free-tier payload, the full-tier payload, and the cost model (x402 USDC on Base at $0.05/call or a Tensorust key). Nothing here contradicts readOnlyHint or openWorldHint=false — the fixed filing corpus is consistent with a closed world.

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 core purpose is front-loaded and no sentence is purely filler, but it is one dense paragraph that blurs data description, statistical marketing, and pricing together. The $0.05/x402 payment terms appear both here and in the schema, which is redundant bulk.

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 by enumerating both tiers' contents (marks, par, prior-quarter mark, filing link). It omits edge-case behavior for companies with no BDC lenders in the corpus, which matters more than usual given openWorldHint=false.

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%, and the schema already documents both parameters including the pricing note, so much of the description's param text is repetition. It does add real meaning the schema lacks: what the free preview actually contains (lowest mark, highest mark, gap, three funds), which lets an agent decide whether to set full=true.

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 and resource: private credit marks for a US company, specifically every BDC fund holding its first-lien term loan, with fair value as a share of par from 10-Q filings. The manager list and the par-relative framing make the output unit unambiguous, and it is distinguishable from siblings like credit_disagreements or credit_q3_cuts.

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?

Clear context for why and when to call it via the predictive statistic (low marks leading peer cuts, 20.4% vs 2.8%), and it spells out the free-vs-full decision explicitly. It does not name a sibling alternative or state when a different tool would be the better pick, so it stops short of full routing 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 and openWorldHint=false, so safety is covered. The description adds genuinely new behavior: free tier returns counts and previews only, full=true returns everything and costs $0.05 per call via x402 USDC on Base or a Tensorust key, including that the tool itself emits x402 payment terms. That said, it omits what happens when the name does not resolve, whether partial matches are returned, or any rate/caching behavior.

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 dense paragraph, front-loaded with the purpose and followed by the tier/pricing split. Some redundancy exists between the description's 'full=true: ... $0.05 per call over x402' and the identical information in the schema, but no sentence is 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?

With no output schema, the description correctly carries the burden of describing return contents by enumeration. For a two-parameter lookup tool with 100% schema coverage and readOnly annotations, the main remaining gap is failure behavior on no-match or ambiguous names, which a resolving tool should specify.

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%, and the schema's own parameter descriptions already explain full=true, the price, x402 payment terms, and the free preview. The description largely restates that same free/full distinction rather than adding new semantics such as name-matching tolerance or acceptable name formats. Baseline 3 applies when the schema does the heavy lifting.

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 ('Resolve a company or organization name to its Tensorust Ontology card') and enumerates the returned content: entity type, data sources, linked objects by type, and applicable federal rules. It is clear what the tool does, though it never names the sibling search_organizations, so the boundary between resolving a known name and searching for one is left implicit.

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 free-preview vs full=true distinction gives a real decision rule, including cost, which is useful. However, there is no guidance on when to use this instead of search_organizations (finding a name) or get_object (fetching a card by id), which are the most likely confusions for an agent.

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 only readOnlyHint and openWorldHint; the description adds substantial context beyond that: truncation behavior (free tier returns only the first 25 names), what the paid tier adds (full named list with evidence), and the exact cost and payment mechanism ($0.25/call over x402 in USDC on Base, or free with a Radar/Ontology key). Cost and result-capping are exactly the operational facts an agent needs before deciding to call.

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 resource and followed by the mode/cost rules; the parenthetical rule examples are dense but earn their place by showing the id conventions. Pricing is repeated in both the description and the schema, which is mild redundancy but justified given the unusual x402 payment model.

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, and the description carries that burden reasonably: it tells the agent to expect counts, organization names, and (on the paid path) supporting evidence, plus the 25-name ceiling. It stops short of describing the record fields for each organization or how evidence is formatted, which leaves some uncertainty about the exact return shape.

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 full parameter's description already spells out the pricing, evidence, and 25-name cap, so the description largely restates schema content. It does add the semantic coupling that full=true only matters when rule_id is supplied ('add full=true'), which is a small value-add over the schema's 'With rule_id' phrasing.

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 the federal rules Tensorust models') and immediately grounds it with five concrete rule examples and the payload shape (counts plus first organizations). This reverse-lookup direction (rule -> organizations) is clearly distinct from sibling tools like lookup_organization and search_organizations, so an agent can route without opening 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?

Gives clear mode selection: omit rule_id to list all rules, pass rule_id for a single rule, add full=true for the complete named list with evidence. It does not explicitly state when to prefer this over the organization-centric siblings (e.g., 'use this to find who a rule touches, not to look up a company'), so the alternative-routing is implied rather than stated.

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 and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: a hard cap of 15 matches and the shape of each result (ids, types, source counts, links), which matters because 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 short sentences, zero filler: the operation comes first and the return contract second. Nothing needs to be trimmed or reordered.

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 single-parameter read tool with annotations covering safety and no output schema, stating the result cap and returned fields makes this largely complete. The remaining gap is the undefined matching behavior and the unspecified scope of "other objects".

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 single parameter has 0% schema description coverage, so the description must carry the meaning. "By name" establishes that query is a name string, but it says nothing about matching semantics (substring vs prefix, case sensitivity) or whether other object types are matched by the same field.

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 ("Search organizations, control groups and other objects by name"), and the title "Search the ontology" adds scope. It stops short of distinguishing itself from the sibling lookup_organization, and "other objects" is left vague, so the agent cannot fully tell the two search-like tools apart.

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: calling it a name search suggests free-text lookup, but there is no explicit when-to-use versus when-not, and the closely related sibling lookup_organization is never mentioned. The agent has to infer routing from the sibling's 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 only cover the read-only and closed-world profile; the description goes further by disclosing that results include the parent control group, portfolio home count, and an institutional-investor classification under the 350+ home ROAD Act threshold. It doesn't describe null/empty behavior when an address is outside coverage, which is the main remaining behavioral 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?

Two sentences with zero filler: capability and returned fields first, then the coverage constraint. The county list is long but is load-bearing for deciding whether to call the tool at all.

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 describing returns and does so adequately: owner of record, parent entity, home count, ROAD Act flag. Combined with the coverage limits, an agent has enough to call and interpret it; only the not-found case is unspecified.

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% and both parameters are already documented with format hints ('5-digit ZIP', example street address), so the schema does the heavy lifting. The description adds only the US-scoping constraint on the address, which the schema does not state.

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 opens with a specific verb and resource plus required inputs: 'Given a US street address and ZIP, return the owner of record.' The home-ownership focus is clearly distinct from aircraft_owner and the organization-lookup siblings, so an agent can route 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?

It gives a concrete applicability envelope: entity-owned single-family homes in 17 named large counties. That tells the agent when the tool will return nothing useful. It stops short of naming an alternative tool to use outside that coverage, so it lands at 4 rather than 5.

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