MacroTape market brief

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

Annotations declare destructiveHint=true and idempotentHint=true, so the core risk profile is covered. The description adds value the annotations do not carry: required key tier (Light/Pro/internal), the exact header form, and that trial keys receive 403. It does not state whether the delete is immediate or recoverable, which is arguably already implied by the destructive hint.

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 action, then auth requirements, all in compact clauses. The trailing 'Informational market data only; not investment advice' is boilerplate that does not help an agent invoke the tool and slightly dilutes 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 single-parameter destructive tool with full annotation coverage and no output schema, the description supplies the missing pieces an agent needs: credential requirement, failure mode for trial keys, and id format. Only the post-deletion effect (irreversible, effects on delivery) is left implicit.

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 0% with one required parameter, so the description must compensate. It supplies the 'wh_...' id prefix, which meaningfully identifies the expected value shape, though it omits where the id comes from. That is a solid but not exhaustive compensation.

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?

Specific verb+resource ('Delete ... webhook alert hooks') with the id format ('wh_...') named, which is more than the name alone conveys. It doesn't explicitly differentiate itself from siblings like list_alert_webhooks or register_alert_webhook, but the action is unambiguous.

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 by the verb and the stated authorization requirement, which is genuinely useful context. However, it never says when to prefer this over alternatives, nor where to obtain the id (e.g., via list_alert_webhooks), so the agent must infer the workflow.

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 read-only/idempotent safety, but the description adds genuinely new operational context: required API key with two accepted header forms, and that calls count against a daily limit. It does not describe error behavior for non-weekday dates or missing editions.

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?

Dense but well front-loaded: resource, format, and edition semantics come first, with auth and rate-limit detail trailing. Every sentence carries load, though the auth sentence is packed enough to slow scanning slightly.

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 is responsible for framing the return, which it does implicitly ('a brief'). Combined with auth, rate limits, date-format constraints, and edition defaults, an agent has enough to invoke it correctly; only failure modes are 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 only 67%, and the description compensates: it adds the 'U.S. weekdays' constraint on date and explains the default behavior when edition is omitted, neither of which is in the schema. The 'format' parameter is left to its enum/default in the schema, which is acceptable.

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 ('A past MacroTape brief by date') with the date format and scope (U.S. weekdays) front-loaded. An agent can distinguish this from get_latest_brief purely from the 'past ... by date' framing.

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 selection logic for the edition parameter (omit -> newest edition that day) and a discovery path ('List available dates with the open /api/index.json'). It stops short of explicitly naming get_latest_brief as the alternative for current briefs, leaving that routing 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 establish read-only, idempotent, closed-world behavior, and the description adds substantively on top: a required Bearer API key, a cost of exactly 1 request, plan-tier caps on history depth (trial 30, Light 365, Pro full series), the [date, value] row shape, and an attribution requirement. It also flags a real provenance caveat (ECB reference rates, not the ICE U.S. Dollar Index), which prevents a plausible misinterpretation.

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?

Coverage and scope are front-loaded, followed by the 'days' semantics, then the return shape, then auth/cost. Every sentence carries an operational fact; the closing 'informational market data only' line is short compliance framing appropriate for a financial data tool.

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 still specifies the return shape ([date, value] rows), the request cost, auth requirements, and depth limits tied to plan tier. Nothing an agent needs to call this correctly or to interpret the response 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 would be 3, but the description adds semantics the schema lacks: the concrete per-plan caps behind 'days' (30 / 365 / full series) and the fact that dxy_style_index is ECB-derived rather than ICE. Those details materially change how an agent sets 'days' and interprets a topic value.

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 ('Daily history for one MacroTape topic') and immediately bounds the data domain: 14 Treasury tenors plus 5 curve spreads since Jan 2, 2025, and 29 FX pairs plus a DXY-style index for the last year. An agent can tell this apart from the sibling brief tools (get_latest_brief, get_brief_by_date) and the alert/webhook tools without inspecting 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?

Usage context is clear: this is the historical time-series endpoint, and '/api/history/index.json' is pointed to as the way to enumerate valid topics. It does not explicitly name get_latest_brief or get_brief_by_date as alternatives, nor state when not to use it, so it stops short of 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?

Goes well beyond the read-only/idempotent annotations: it specifies the two accepted auth header formats, that calls consume the key's daily quota, the edition freshness model, and the as_of quoting caveat. This is exactly the operational context annotations can't 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?

Front-loaded with purpose and payload, then auth and cost. Dense but nearly every clause carries information; the closing 'not investment advice' is the one piece of boilerplate, though it is arguably relevant for market data.

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 still conveys the return contents and the difference between the two response formats, plus auth, quota, and freshness requirements. Nothing an agent needs to invoke it 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% and the enum description already defines text vs json, so the baseline is 3. The description adds a cost dimension ('cheapest') and restates the payload shape per format, giving marginal value 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?

States a specific verb and resource ('Latest MacroTape market brief') and enumerates the exact contents: Treasury par curve, spreads, curve shape, ECB currencies vs USD, top movers, dollar breadth. 'Newest weekday AM/PM edition' implicitly separates it from get_brief_by_date, 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 selection signals: use this for the newest edition, and format=text is the 'cheapest' option while json is the full brief. It does not explicitly name alternatives like get_brief_by_date or get_sample and when to prefer them, so it falls short of full when/when-not 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?

The annotations already cover read-only, idempotent, and closed-world behavior. The description adds meaningful context that no API key is required and that format=text returns one compact line, though it does not discuss rate limits or JSON-specific 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?

The description is three tight sentences with no waste. It front-loads the core purpose and follows with access and format details, each of which is useful.

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 one-parameter sample tool with no output schema, the description covers purpose, access requirements, covered data points, and text formatting. It could be slightly more complete by describing the JSON return shape or clarifying how the sample differs from a full brief.

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 explains that format=text produces a compact line, adding practical meaning beyond the enum and default; JSON behavior is only implied but still reasonably clear for a single optional parameter.

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 that this returns a free headline sample of the latest brief, including the specific data points covered. It distinguishes itself somewhat by being a 'sample,' but it does not explicitly contrast with the sibling get_latest_brief tool.

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 provides useful access context ('Open, no API key needed'), implying this is the lightweight/free option. However, it does not explicitly say when to use this instead of get_latest_brief or get_history, nor does it state limitations or exclusions.

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, idempotentHint=true, openWorldHint=false), so the bar is lower. The description still adds real context: secrets are deliberately excluded from the response, the required credential format ('Authorization: Bearer <key>') and the fact that trial-tier keys fail with 403. Missing only secondary traits such as rate limits or result ordering.

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 sentence is front-loaded and dense with useful facts, and the auth constraint follows immediately. The trailing 'Informational market data only; not investment advice' is legal boilerplate that does not help an agent select or invoke the tool, costing it a point.

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?

Even without an output schema, the description explains what comes back (hooks, plan, hook limit, secrets redacted) and which credentials are required or rejected. For a parameterless read tool this covers everything an agent needs before calling it.

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 and the input schema is a closed empty object at 100% coverage, so the baseline is 4. There is nothing further the description could add about arguments.

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 webhook alert hooks registered for your API key') and names exactly what is returned (hooks, plan, hook limit) with a scope qualifier ('no secrets'). It is clearly distinguishable from register_alert_webhook, delete_alert_webhook and test_alert_webhook 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?

Usage is implied by the name and by the auth requirement ('Needs an API Light, Pro or internal key... trial keys get 403'), which tells the agent whether it can call it at all. However, it never says when to prefer this over get_latest_brief, get_history or the register/delete/test siblings, so the routing guidance 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 readOnlyHint, idempotentHint and closed-world, so the safety profile is covered. The description adds genuinely new context beyond them: no authentication/API key is required, which is an operational fact an agent cannot get from the annotations. It does not mention result size or whether the catalog is static, which keeps it from a 5.

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, front-loaded with what the caller gets, followed by the access note. No filler, no restatement of the name or title.

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 usefully spells out the per-entry fields (JSON field path, unit, source), which is the key thing an agent needs in order to use the result for subsequent queries. What remains unstated is the approximate volume of the response and whether ordering is stable, a minor gap for a no-parameter tool.

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 baseline is 4 and there is nothing for the description to compensate for. The schema is fully closed (additionalProperties: false, empty properties), consistent with a no-argument catalog call.

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 enumerates exactly what the tool returns: every queryable subject (Treasury tenors/spreads, FX pairs, aggregates) along with its JSON field path, unit and source, which is effectively a schema catalog. That is specific enough to distinguish it from every sibling (history, briefs, samples, alert webhooks). It lacks an explicit verb, relying on the name/title for the 'list' action, so it falls just short of 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?

'Open, no API key needed' states an access prerequisite, and the content of the return (field paths) implies the natural workflow of calling this before get_history. But the description never says when to use this versus get_history/get_latest_brief or that it is a discovery step, leaving the sequencing 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 only say non-readonly, open-world and non-idempotent; the description goes well beyond that with the one-time signing-secret return, the exact signature header format, the bearer-token auth requirement and the trial-key 403 failure mode. That is exactly the operational context an agent needs before calling a write endpoint.

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 action and trigger, and no sentence is purely filler; the signature-format and auth sentences carry real information. The trailing compliance disclaimer ('not investment advice') is boilerplate and the nested parentheses make it denser than it needs to be.

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 explains the return value (signing secret returned once) and covers auth and failure modes. What is missing is behavior on re-registering the same URL or limits per key, small but relevant gaps for a non-idempotent create.

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 67% and the description compensates by explaining the semantics behind both enum values — the 10bp Treasury threshold and the DXY-style index built from ECB reference rates, explicitly not the ICE U.S. Dollar Index. Only the 'description' field's purpose is left untouched, so it falls just short of full coverage.

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 ('Register an https URL to receive signed JSON alerts') and pins down the exact trigger conditions (10y par yield >10bp, DXY-style index >1%). It never names the sibling endpoints, but the verb 'Register' is unambiguous against list/delete/test_alert_webhook,

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?

States a prerequisite — a Light/Pro/internal key is needed and trial keys get 403 — which tells the agent when the call will succeed. It does not say when to prefer this over alternatives, whether duplicates of an existing URL are allowed, or how to inspect current registrations via list_alert_webhooks.

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?

Goes well beyond the annotations by disclosing a real side effect not captured anywhere structured: a successful ping re-enables a disabled hook. It also documents the auth requirement (API Light/Pro/internal key via 'Authorization: Bearer <key>') and the failure mode for trial keys (403), which the openWorldHint/idempotentHint flags do not convey.

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 action and effect, followed by side effect, auth, and a short disclaimer. Every sentence is doing work, though the trailing legal disclaimer is boilerplate rather than operational guidance.

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 one-parameter tool with no output schema, the description covers the action, the side effect, the auth/prerequisite requirements, and what is returned ('report the receiver's HTTP status'). An agent has everything needed to invoke it 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 0% for the single required 'id' parameter, so the description must compensate and only partially does: 'one of your hooks' implies the id selects a registered webhook, but it never states that explicitly or gives the identifier's form. It adds context but leaves the parameter's exact meaning to inference.

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 ('send one signed test.ping event to one of your hooks') with the effect ('report the receiver's HTTP status'). This is clearly distinguishable from siblings like register_alert_webhook, list_alert_webhooks, and delete_alert_webhook 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?

Gives clear context for use — testing a hook now, and the notable condition that a successful ping re-enables a disabled hook, which tells the agent when this tool matters. It does not explicitly name alternatives or state when not to use it, so it falls short of a 5.

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