BrinkerAdvisor Rates

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

With all annotations false and no safety hints, the description carries the full behavioral burden and does so thoroughly. It discloses that rungs must contain a canonical brinkeradvisor_url plus source_name and source_url, that uncovered rungs are returned explicitly, and that the tool performs no account access, trading, recommendation, forecasting, or advisory functions. This is valuable context beyond any structured annotation.

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 tight, front-loaded with the trigger, and packs the key constraints into three sentences. The link requirement sentence is slightly repetitive ('for every covered rung' appears twice), but overall the structure is efficient and easy to parse.

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 the output schema exists, the description does not need to explain return structures, but it still provides essential user-facing display requirements and behavioral boundaries. It covers the trigger, supported instruments, link obligations, and non-advisory scope. It could be more complete by addressing what happens when no eligible options exist or how hypothetical_amount_usd influences results, but these are minor gaps.

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 compensate. It meaningfully maps instrument_types to the listed public CD/money-market/Treasury/municipal options and interprets rung_count and term range. However, it does not explain minimum_term_months vs maximum_term_months relationships, rung_count constraints, or the optional hypothetical_amount_usd parameter, leaving part of the parameter burden unmet.

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 begins with a specific trigger: 'Use when the user asks for an educational equal-weight maturity ladder...' It names the exact resource (maturity ladder), the instrument types (CD, money-market, Treasury, municipal), and the key parameters (rung count and term range). This clearly distinguishes it from siblings like compare_rates, fetch, and search, 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 gives an explicit when-to-use condition ('Use when the user asks for...') and strong exclusions ('never accesses accounts, trades, recommends a product, forecasts rates or the economy, or provides suitability or tax advice'). However, it does not name alternative sibling tools or explicitly explain when to prefer compare_rates, fetch, or search instead.

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 are all false and add no safety profile, so the description carries the burden. It discloses what the tool returns (applied filters, current options, comparability limitations) and that it avoids selecting a winner, plus the canonical-link requirement. It does not discuss side effects, but a comparison tool with no positive hints is adequately transparent.

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 dense but front-loaded: the main purpose and trigger condition come first, followed by output behavior, link handling, and exclusions. Every sentence contributes, though the 'outside comparison intent' and 'Do not use for' sentences partially overlap.

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?

It covers the main purpose, invocation condition, output contents, link requirements, and major exclusions. With an output schema present, the lack of explicit return-format details is acceptable; only minor details like how 'implied' filters get resolved are 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 description coverage is 0%, so the description should compensate for parameter meaning. It only refers generically to 'instrument and maturity filters' and 'bounded' comparison, never naming limit, minimum_term_months, maximum_term_months, or their constraints. The schema names help, but the description adds little semantic value beyond the structured fields.

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 uses a specific verb-resource pair ('Create a bounded side-by-side comparison') and names the instrument categories (CD, money-market, Treasury, municipal), clearly distinguishing from the sibling search/fetch tools by excluding find/list requests and instructing not to call fetch.

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 explicitly states the trigger condition ('only when the user explicitly asks to compare, contrast, versus, or vs current ... options') and provides detailed exclusions: find/list requests, economic/Fed forecasts, account actions, personalized advice, tax advice, suitability. It also tells the agent not to fall back on fetch for links.

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?

The description adds useful behavior beyond annotations: it guarantees a single-record return and prescribes how the final answer must present url vs. metadata.source_url. However, the annotations declare readOnlyHint, idempotentHint, and openWorldHint all false, and the description does not address why a lookup-type tool would carry those flags or disclose any side effects, failure behavior, or not-found handling.

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?

Three sentences with zero filler. The primary verb-resource-scope claim is front-loaded, the input requirement is the second sentence, and the output-presentation rule earns its place as a concrete agent-facing instruction. 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?

For a simple single-parameter lookup with an output schema present, the description covers the input precondition, the return cardinality, and the output formatting rule. Minor gaps remain: no mention of not-found/error behavior and no explicit route to search when the ID is unknown, but these are small against the tool's simplicity.

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 bare schema only states id is a string of 1–200 chars. The description compensates meaningfully by clarifying that the id must be an exact, stable, already-known record identifier rather than a search term or fuzzy query—real semantic content 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 states a specific verb ('Retrieve'), a specific resource ('one current public BrinkerAdvisor record'), and enumerates the exact fields returned (yield, term, freshness, canonical link, provenance). The scoping condition 'when its exact stable record ID is already supplied' sharply distinguishes it from the search sibling without 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?

The description gives clear usage context: it is for the case where an exact stable record ID is already in hand ('Requires one known ID and returns one record'), which implies search is the alternative when no ID is known. However, it never names the sibling tools explicitly nor states when-not-to-use conditions.

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 are all false/neutral, so the description carries the behavioral burden. It clearly discloses return contents (stable IDs, titles, canonical URLs) and adds a specific output requirement (every URL must be a clickable link, not summarized by IDs). The 'find or list' wording implies a read-only discovery operation, and the public-records framing covers access context.

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 front-loaded with the core purpose, then provides usage conditions, return details, output formatting instructions, and exclusions in a logical order. Every sentence adds operational value for the agent, and there is no redundant or filler content.

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 the output schema exists and annotations are neutral, the description covers scope, query semantics, return contents, output formatting, and domain exclusions. It does not mention result limits, sorting, or empty-result behavior, but those are minor for a simple discovery tool with a single query parameter.

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 for the single 'query' parameter is 0%, so the description must compensate. It does by explaining that query can express product, institution, term, or maturity, and that the request can be phrased as find, search, list, browse, look up, show, or link. It stops short of giving query syntax examples, but for a single free-text parameter this is meaningful guidance.

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 ('Find or list') and a precise resource ('current public BrinkerAdvisor CD, money-market, Treasury, or municipal rate records'), and identifies search criteria. It also distinguishes discovery requests from comparison and exact-ID lookups, making it easy for an agent to separate this tool from its 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?

The description explicitly says when to use the tool: for find/search/list/browse/look up/show/link requests when no exact stable record ID is supplied, and clarifies that multi-record requests are discovery, not comparison. It also lists many exclusions (economic indicators, forecasts, account access, etc.), but it does not explicitly name the sibling tools to use instead in those excluded cases.

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