MacroTape market brief

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 cover read-only/idempotent safety, but the description adds substantial context beyond them: required API key with two accepted header formats, daily-limit accounting, the as_of quoting caveat, and a not-investment-advice disclaimer. This is exactly the auth/rate-limit 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?

Front-loaded with the tool's identity, then format options, then auth requirements. The section enumeration is dense but justified for selection. Slightly long, yet no sentence is pure 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 still conveys content scope, format tradeoffs, auth mechanics, and rate-limit behavior. There is no output schema needing explanation, and 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% for the single format parameter, so baseline is 3. The description adds value beyond the schema by tying text to 'cheapest' and json to the 'full structured brief', giving a cost/richness tradeoff the schema enum 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 specific resource (latest MacroTape market brief for the newest weekday AM/PM edition) and enumerates the content sections. An agent can distinguish it from get_brief_by_date by the 'latest' scope, though the sibling is never named explicitly.

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 format selection (text = cheapest compact line, json = full structured brief), which is implicit usage guidance. However it never states when to prefer this tool over get_brief_by_date or get_sample, nor any 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 declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety is covered. The description adds genuinely new context beyond them: no API key is required (an auth/access trait annotations do not express) and a hint at the output shape ('one compact line'). It stops short of describing response structure in depth, but for a read-only sample that is a reasonable level.

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 short sentences, zero filler, with the core value proposition (free, no key) and the format hint front-loaded and easy to scan. Every sentence carries information the schema and annotations do not.

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?

There is no output schema, so the description has to carry return-value information, and it does: it enumerates the instruments covered and describes the text output as one compact line. The json variant's shape remains unspecified, which is the one remaining gap for a tool with no output schema.

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 burden is on the description, and it only half-compensates: it explains what format=text produces but says nothing about what format=json returns or why one would choose it. The enum values and default are self-evident from the schema, so the added meaning is real but partial.

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 resource and scope: a free headline sample of the latest brief, with the exact content covered (2Y/10Y, 2s10s, curve shape, EURUSD/USDJPY, BTC/ETH). It implicitly separates itself from get_latest_brief by being a 'sample' rather than the full brief, but it never names that sibling, so the differentiation is inferential rather than explicit.

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' plus 'Free' strongly implies the use case (quick, unauthenticated peek without credentials), which is real guidance. However, it never explicitly states when to prefer this over get_latest_brief or get_brief_by_date, leaving the agent to infer the routing from the word 'sample'.

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 readOnly, idempotent, and closed-world, so the bar is lower. The description adds genuine behavioral context beyond them: the auth condition ('no API key needed') and the shape of each returned entry (field path, unit, source). It omits pagination or ordering behavior, but for a small static catalog that 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?

Two compact sentences with no filler. The content enumeration is front-loaded and the access constraint is appended rather than buried, so every clause earns its place.

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?

There is no output schema, so the description must carry the return contract, and it does: list of subjects each carrying field path, unit, and source. No input parameters need explaining. Only the exact container/format (array vs. object, sorting) is left unspecified, which is minor for a simple catalog endpoint.

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 baseline of 4 applies. There is nothing for the description to document beyond confirming the tool is unfiltered and takes no 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?

The description names a concrete resource (every queryable subject: Treasury tenors/spreads, FX pairs, crypto assets, aggregates) and specifies the per-item payload (JSON field path, unit, source). It is clearly a catalog/discovery tool, distinct in kind from the brief-fetching siblings, but it never explicitly names or contrasts with those 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?

Usage is only implied: an agent can infer this is the lookup you call to discover valid subjects/field paths before querying. There is no explicit when-to-use statement, no exclusions, and no routing against get_brief_by_date, get_latest_brief, or get_sample. 'Open, no API key needed' is an access note, not usage guidance.

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