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

No annotations are provided, so the description must fully disclose behavior. It states the tool returns up to 25 ranked programs with specific fields, which is informative. However, it does not mention authentication needs, rate limits, or any side effects, but these are not critical for a search tool.

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 description is two sentences: first defines purpose and output, second gives usage examples. No wasted words, front-loaded with key info.

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?

The tool has 5 parameters (all optional) and no output schema. The description covers what is returned and the filtering logic. It does not mention error cases or pagination, but for a search tool, the level of detail is sufficient.

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%, with each parameter well-described (e.g., state: 'Two-letter US state code...'). The description provides overarching context but adds little to individual parameter meaning. 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?

The description clearly states the tool finds Down Payment Assistance programs with specific filters (state, county, FTHB, type). It lists returned fields (URLs, eligibility, amount, program type). This distinguishes it from sibling tools like cal_fact_lookup or cal_lender_details, which serve different purposes.

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 description explicitly lists example queries ('DPA in <state>', 'first-time buyer help in <county>') and program types (grant, MCC, etc.), providing clear when-to-use guidance. It implies when not to use by focusing on DPA, and sibling tools cover other areas.

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?

No annotations are provided, so the description carries the full burden. It discloses the return format ('value with source citation'), scope ('all 50 US states + DC, all county-level limits, 1-4 unit properties'), and the fact that values reset annually. It does not mention error handling or rate limits, but for a read-only lookup this is sufficient.

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 description is a single paragraph of 4 sentences, front-loaded with purpose and a list of facts. Every sentence adds value: purpose, usage rule, return format, and coverage. No wasted words.

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 lookup tool with no output schema, the description adequately explains what is returned (value with source citation) and the extent of coverage. It names the authoritative sources (FHFA, HUD, VA, Fannie/Freddie). The 6 parameters are fully covered by schema descriptions and the extra context in the description makes it complete.

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 baseline is 3. The description adds value by clarifying formatting conventions (e.g., 'lowercase with underscores' for county, 'both work' for spaces/underscores), default behavior for units, and the purpose of each parameter (e.g., va_down_payment_pct is for bracket selection). This goes beyond the schema descriptions.

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 clearly states the tool's purpose with specific verbs ('look up') and resources ('authoritative 2026 mortgage facts'). It explicitly lists the fact categories (FHFA limits, FHA limits, VA fees, etc.), distinguishing this from sibling tools like cal_scenario_pattern or cal_search_lenders, which are about scenario analysis or lender search.

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 description provides explicit guidance: 'Use this whenever you need a specific dollar amount, percentage, or threshold — never quote these from training-data memory'. It also warns about the difference between FHFA and FHA programs, and specifies coverage (all 50 states, county-level). This helps the agent decide when to invoke this tool over 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?

No annotations are provided, so the description carries the full burden. It describes a fetch operation without side effects, but does not explicitly state that it is read-only or safe. The behavioral implications are inferred but not confirmed.

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 description is two sentences, front-loaded with the core action, and contains no extraneous information. Every word serves a purpose.

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 lists key return fields, providing adequate context. However, it does not mention pagination, error conditions, or rate limits. Given the low complexity, this is sufficient but not complete.

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% for the single parameter. The description does not add any additional meaning beyond what is in the schema (e.g., format or usage hints). Baseline score 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 explicitly states the tool fetches the full record for a specific wholesale lender, listing concrete data fields (programs, licenses, contact, portal URL, status, matrix dates). It clearly distinguishes from the sibling cal_search_lenders by specifying the use case after that search.

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 description provides clear usage context: 'Use this after cal_search_lenders to get contact details + portal info before recommending the lender to an LO.' It implies a sequential workflow, though it does not explicitly state when not to use it or alternatives beyond the sibling.

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?

No annotations are provided, so the description must carry the full behavioral burden. It states returns and sorting but does not explicitly disclose that the operation is read-only or lacks side effects. The implied read behavior is clear, but explicit declaration would improve transparency.

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 description is concise, using two well-structured sentences. The first sentence enumerates outputs and sorting, the second provides usage guidance. No superfluous text.

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 simple list tool with one parameter and no output schema, the description covers purpose, usage context, returned fields, and sorting order. It lacks details about potential empty results or data freshness, but is largely complete.

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?

With 100% schema description coverage for the single parameter 'lenderSlug', the baseline is 3. The tool description does not add additional meaning beyond the schema, which already explains the slug format. No further parameter semantics are provided.

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 clearly states the tool's purpose: listing indexed documents for a lender, specifying what fields are returned and the sort order. It distinguishes itself from sibling tools by focusing on documents (matrices, handbooks, overlays) rather than lender details or fact lookups.

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 description provides explicit context for when to use this tool: 'to verify program details or cite a specific matrix version when answering an LO question.' However, it does not mention when not to use it or suggest alternative tools.

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?

No annotations are present, so description carries the burden. It explains the tool returns intelligence data and that passing intent can save tokens. While it doesn't disclose potential limitations like data freshness, the behavioral context is adequate for a read-only intelligence tool.

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?

Single paragraph is concise but well-structured: begins with purpose, then usage guidelines, then parameter advice. Every sentence adds value with no redundancy. Front-loaded with key 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?

Given no output schema, the description explains the return content (strengths, watch-outs, etc.) and how to narrow response via intent. It covers all needed context for an agent to select and invoke the tool correctly, including relationship to sibling tools.

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 good base descriptions. The description adds significant value: explains intent parameter with enum values and default, gives example usage ('e.g. intent="scenariosTheyLove"'), and clarifies that lenderSlug must match cal_lender_details. This goes well 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?

Description clearly states the tool provides tribal-knowledge intelligence on a wholesale lender, listing specific aspects like strengths, watch-outs, speed notes, and AE contacts. It distinguishes from sibling tools by specifying usage after cal_lender_details and targeting qualitative questions.

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 says to use after cal_lender_details, for qualitative questions like 'is this lender any good for X?' or 'fastest path'. Provides examples of when to pass an intent to narrow response and save tokens, offering clear when-to-use and when-to-avoid 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?

No annotations are provided, so the description carries full burden for behavioral disclosure. It explains the tool returns a playbook (lender shortlist + guideline) and is read-only in nature. While it doesn't explicitly state no side effects, the description is transparent about its output and purpose.

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 description is two sentences, front-loaded with the tool's purpose and followed by a list of examples. Every word earns its place with no redundancy or fluff.

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 simple lookup tool with one enum parameter and no output schema, the description adequately covers what the tool does, what it returns, and when to use it. Some might prefer an explicit note about no side effects, but overall it is complete.

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% with enum values described in the schema. The description reinforces that each pattern corresponds to a specific playbook but doesn't add significant new meaning beyond the schema's own descriptions. 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?

The description clearly states the tool fetches a structuring playbook for recognized hard mortgage scenarios. It lists specific patterns and explains the output (lender shortlist + guideline). This distinguishes it from sibling tools by positioning it as a first step before lender searches.

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 description explicitly says 'Call this FIRST when the LO's question matches one of these patterns' and implies not to use it for other questions. It provides clear context for when to invoke this tool vs alternatives like cal_search_lenders.

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?

With no annotations, the description carries full burden. It discloses that results are ranked best-first with score, qualifying reasons, and blockers (state license gaps, FICO/LTV overlays). It mentions use of a live library and default behavior. However, it does not state whether the operation is read-only or idempotent, 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 description consists of three concise sentences with no wasted words. The first sentence front-loads the purpose, the second provides usage guidance, and the third explains defaults. Every sentence adds value.

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?

Despite no output schema, the description explains what is returned (lenders ranked with score, reasons, blockers) and mentions defaults and expansion. It is mostly complete for a search tool, though it could specify the output structure (e.g., list of objects) and whether results are real-time or cached.

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?

All 9 parameters have descriptions in the schema (100% coverage), so baseline is 3. The description adds context by grouping parameters as scenario details (FICO, LTV, loan amount, occupancy) and mentioning defaults for expand and includeBlocked, but it does not provide significant additional meaning 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?

The description clearly states 'Search Cal's scoped wholesale-lender library for programs that fit a loan scenario,' specifying the verb (search), resource (wholesale-lender library), and purpose (fit a loan scenario). It distinguishes itself from sibling tools like cal_lender_details and cal_dpa_search by focusing on lender discovery.

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 description explicitly advises using this tool for 'who does X?' or 'which lender for Y?' questions and recommends passing as much scenario detail as possible. It provides context on defaults (top 5, expand for top 15) but does not explicitly state when not to use it or list alternatives, leaving some ambiguity.

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?

No annotations are provided, so the description carries full weight. It describes the output (market value, range, verdict, confidence, percent above/below, comps used) and inputs. It does not mention any side effects, but the tool is clearly analytical and non-destructive.

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 description is two concise paragraphs. The first paragraph defines the tool's action and outputs; the second gives usage guidance and requirements. Every sentence is necessary and well-structured.

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 no output schema, the description thoroughly covers the return values. It also details the input structure and constraints (min 4 comps, optional fields). For a tool with nested objects and optional parameters, this is fully complete.

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%, but the description adds significant context: explains 'opts' as tuning parameters, notes 'listings' requires at least 4, and states that more comps increase confidence. This goes beyond the schema's field descriptions.

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 clearly states the tool performs a comparable-sales valuation and returns a list-price rebuttal. It explicitly lists inputs and outputs, distinguishing it from sibling tools which are unrelated (e.g., lender searches).

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 description gives explicit use cases: 'is this list price fair', 'what is this home worth', appraisal-gap or list-price-rebuttal questions. It also clarifies what the tool does not do (fetch comps) and what the caller must supply.

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