LenDb.ai

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 is fully covered by structured data. The description's statement of returned content (what it is, why it is hard, questions to ask, synonyms, canonical_url) is largely redundant with the output schema. It adds no rate limits, auth requirements, or failure behavior, so a 3 is fair.

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 trigger condition before the return description, and zero filler. Every clause carries information the agent can act on.

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 lookup with a fully described schema, complete annotations, and an existing output schema, the definition supplies everything needed: when to invoke it, what the slug represents, and that it is scoped to one specialty at a time. 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 coverage is 100% and the slug parameter already carries the full enumerated vocabulary, so the schema does the heavy lifting. The description's examples of natural-language surface forms ('a DSCR loan', 'an ITIN loan') add mild value in mapping user phrasing to the slug, but no syntax, format, or edge-case guidance beyond that. Baseline 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?

States a specific verb (explain) and resource (a mortgage specialty), and enumerates concrete surface forms (DSCR loan, bank statement loan, ITIN loan, non-warrantable condo, FHA loan) so the agent knows exactly what domain this covers. It is clearly distinguishable from list_specialties (enumeration) and the get_* sibling tools (entity lookup).

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: 'Use this when someone asks what a mortgage loan type or borrower situation means.' That is clear when-to-use context, and the examples reinforce it. It does not name an alternative or a when-not condition (e.g., use list_specialties to discover valid slugs), 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 only declare this as a safe read; the description adds substantial behavior: partial coverage, lender-neutral ranking, radius widening from 25 to 50/100 miles with a search.note, statewide ranking for state-only queries, lender-kind boosting, a separate not_yet_verified bucket, ambiguous_location and unassessed_requirements signals, and the explicit guarantee that phone and email are never 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?

It is front-loaded with the trigger condition and stays in one dense paragraph with little filler. However, a long tail enumerates return fields (name, NMLS ID, distance_mi, canonical_url) that an output schema already covers, making the closing sentences partly redundant.

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 6-parameter tool with an output schema and read-only annotations, the description covers everything needed to call it correctly: input interpretation, ranking behavior, geographic widening, data-coverage caveats, and safety/privacy limits. 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 coverage is 100%, so the baseline is 3; the description goes further by explaining how location behaves (city/ZIP radius, state-wide ranking) and how situation free-text is interpreted (words like 'broker' or 'credit union' boost lender kind). It does not touch limit, debug, or fha_approved in prose, but those are already fully 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?

The description names a specific verb and resource (find US mortgage loan officers) and scopes it to a situation plus a place, with concrete examples of loan programs and borrower types. It is distinguishable from get_loan_officer (lookup of a known person) and get_lender 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?

The opening sentence gives an explicit trigger condition ('Use this when someone wants a US mortgage loan officer ... for a specific situation and place'), which is strong. It does not explicitly exclude or route to siblings such as get_loan_officer for a named person, so the agent must infer the boundary.

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 (readOnly, idempotent, non-destructive), but the description adds substantive semantics: 'absent means no HUD match on file, not that the lender lacks approval', the same caveat for HMDA, and the meaning of includes_brokered=true. These absence-vs-negative distinctions are exactly the kind of behavioral context annotations cannot express.

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?

It is front-loaded with the usage clause, and the citation-format and absence-semantics fragments earn their place. However, the long middle enumerates return fields (type, HQ state, website, programs, activity counts, disciplinary_check, verified date, canonical_url) that an output schema already defines, making one run-on sentence heavier than necessary.

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 an output schema present, return values need not be described, yet the critical non-schema caveats (absence meaning, HMDA attribution format) are included, so an agent can call and interpret the result correctly. It is slightly over-complete on return fields, 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?

The single parameter has 100% schema coverage and the schema already documents 'digits or all or part of the company name', which is precisely what 'a partial name works' restates. The description adds no new syntax or format guidance 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?

States a specific verb (get facts about) plus a precisely scoped resource ('a US mortgage lender, bank, credit union or mortgage broker company') and the two lookup keys. The domain is cleanly distinguished from the loan-officer and specialty siblings by naming the entity type it returns facts about.

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?

'Use this when you need facts about a US mortgage lender... by its company NMLS ID or by name (a partial name works)' gives clear triggering conditions and lookup modes. It stops short of naming the alternatives (get_loan_officer, find_loan_officers) or stating when to prefer them, so it is context without explicit 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 already cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on real behavioral context: US-only scope, the meaning of disciplinary_check='not_checked', the last-verified date, and an explicit statement that phone/email are withheld pending human check. That is meaningful disclosure beyond what the structured fields 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?

The usage trigger is front-loaded and the response inventory is packed into one dense sentence with no filler. It is on the long side and the field enumeration reads as a run-on, but every clause conveys usable information.

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 lookup tool this is complete: it covers the identity model, geographic scope, data provenance ('LenDb's sourced record'), known gaps (no phone/email, unchecked discipline), and freshness. The output schema exists, so the return-field listing is a bonus rather than a necessity.

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 is fully documented in the schema (digits only, example 452476). The description only restates that the ID is the individual officer's NMLS ID, adding marginal meaning over the schema — 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 ('Get a loan officer') keyed by the identifying attribute ('by NMLS ID'), which cleanly separates it from the sibling find_loan_officers search tool and from get_lender. An agent knows exactly what entity this returns 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 a clear trigger condition: use it 'when you have a mortgage loan officer's individual NMLS ID and need their full profile' — implying a known-ID lookup rather than a search. It does not explicitly name find_loan_officers as the alternative for name/state lookups, so the routing guidance 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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds the completeness guarantee ('every specialty', i.e. no filtering or pagination) and notes that supported languages are included, which is modest extra context rather than rich behavioral disclosure.

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 usage condition, followed by the return contract; both sentences earn their place. The long enumeration of example specialties (FHA, VA, USDA, jumbo, DSCR...) is helpful for semantic matching but is the wordiest part of the definition.

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-parameter, read-only listing tool with full annotations and an output schema, the description supplies everything an agent needs: when to call it, that the result is exhaustive, and the shape of each entry. Return-value detail is technically redundant with the output schema but does not leave any 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?

The tool takes zero parameters, so the schema carries no semantics to clarify and the baseline of 4 applies. Nothing in the description is needed or misleading on this dimension.

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 every specialty') and enumerates exactly what comes back: slug, category, label, one-line description and canonical_url. The scope word 'every' plus the use-case framing ('the mortgage situations LenDb can match on') separates it from the single-item sibling explain_specialty without the agent needing to open 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?

'Use this when you need the mortgage situations LenDb can match on' gives an explicit trigger condition. However, it never names an alternative (e.g. explain_specialty for one specialty) or states when not to use it, so the routing guidance is clear but not complete.

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