Livestock Market Prices

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the semantic rule that configured sources are not 'covered' until eligible observations exist. That meaningfully changes how an agent interprets the output and goes beyond the annotations.

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 is described and followed by the one interpretive caveat. Minor awkwardness in the phrasing of the first sentence, but nothing is wasted.

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?

An output schema exists so return shape need not be restated, and the description tells the agent which coverage dimensions to expect plus the key eligibility caveat. It is sufficient for a zero-argument read tool, with only the lack of usage context as a residual 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?

This tool takes zero parameters, so the schema-baseline is 4 and there is no parameter syntax for the description to compensate for. No omission exists to penalize.

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 (describes) and resource (publishable sheep, goat, and cattle coverage, broken into market, species, date coverage, and freshness). This is clearly distinct from get_latest_prices and get_methodology, though it never names a sibling to sharpen the contrast.

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: a coverage tool is naturally used to check data availability before pulling prices or reports, but the description never says when to call this versus the sibling tools or what prerequisite it satisfies. No explicit when/when-not guidance is present.

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, non-destructive behavior, so the bar is lower. The description adds real context beyond them: results are bounded, limited to 'reviewed, rights-eligible' records, carry dataset revision and limitations, and San Angelo records are separately labeled rather than counted as Central Texas member data. What it does not state is the bound itself or any pagination 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 first sentence is well front-loaded and the return-value inventory is dense but efficient. The final sentence about San Angelo labeling is a narrow edge case that consumes a third of the text, and the middle sentence reads like a field dump rather than 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?

An output schema exists, so the description's long enumeration of returned fields is partly redundant, while the genuinely useful information — how to use the 8 undocumented filter parameters — is absent. Adequate for a simple read call, but not complete for a tool with this many enums and patterns.

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% across 8 parameters, so the description must carry the burden and largely does not. It gestures at species ('goat, sheep, or cattle') and 'weight bands,' but gives no meaning for class, purpose, location syntax, weight_lb units, breed_type, or the limit cap. Most filter parameters remain semantically opaque.

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 gives a specific verb and resource: 'Returns a bounded list of ... published goat, sheep, or cattle observations.' That is enough to distinguish it from get_methodology and get_data_coverage, though it never names a sibling tool outright. Clear purpose, but sibling differentiation is left implicit.

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?

There is no when-to-use guidance, no statement of prerequisites, and no mention of alternatives such as get_market_report or get_usda_cattle_benchmark. The agent must infer usage purely from the tool name and the surrounding tool set.

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, closed-world), so the description earns credit for adding a genuinely new confidentiality contract: no raw private artifacts, no unpublished extraction output, no internal review notes, no bucket keys. That tells the agent what it will never receive and implicitly that missing data is by design rather than an error.

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 return contract before the exclusion list. Nothing is padded; the negative-scope sentence is long but does real work by preempting futile data requests.

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?

An output schema exists, so return-value shape need not be described, and annotations carry the safety profile. The remaining gap is minor: how the observation_limit cap manifests (truncation vs. error) and what a bad or unpublished report_id produces is unstated.

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 schema documents constraints but not meaning. The description gestures at both parameters — 'one published report revision' maps to report_id and 'bounded observation projection' maps to observation_limit — but adds no format, default, or cap detail beyond what the schema's pattern/maximum already enforce.

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 one published report revision plus a bounded observation projection. It's clear what the tool yields, but it never names or contrasts itself with siblings like get_latest_prices or get_methodology, so an agent still has to infer which report-shaped tool applies.

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?

There is no statement of when to call this versus the other get_* tools, and no prerequisites (e.g., needing a valid report_id from a prior listing call). The only scope language is about what the service refuses to expose, which is a boundary, not usage 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 already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and a closed world, so the safety profile is covered. The description adds real value by classifying the content (calculation rules and limitations) and explicitly denying that it produces a forecast or guaranteed price. It does not address what happens when 'version' is omitted or whether versions expire, which would be the remaining behavioral 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 sentences, zero filler, and the positive statement of purpose is front-loaded while the disclaimer follows. 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?

An output schema exists, so return structure need not be described, and annotations cover the safety profile. The remaining gap is the optional 'version' parameter's default behavior on omission, which is undocumented in both schema and description for a tool whose whole purpose is versioned retrieval.

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 'version' parameter has 0% schema description coverage, so the description carries the burden. It references the 'requested published methodology version', loosely tying the parameter to the concept, but never states what happens when version is omitted (it is optional) or what valid identifiers look like. Partial compensation, not full.

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 gives a concrete verb and resource ('Returns the requested published methodology version') and enumerates the payload ('exact calculation rules and limitations'), so the agent knows what it retrieves. It also draws a boundary against forecast/appraisal outputs. It stops short of naming which sibling to use instead, so sibling differentiation is only partial.

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 rather than stated: an agent can infer this is the tool for understanding how prices are calculated, and the negative scoping ('does not create a forecast, appraisal, or guaranteed selling price') usefully rules out a common misreading. However, there is no explicit when-to-use guidance relative to get_latest_prices, get_market_report, or get_data_coverage.

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, non-destructive, closed-world behavior, so the description's job is to add semantics — and it does, noting the data is 'reviewed', that it preserves the original reporting period and quote units, and warning that per-head and pair quotes must not be read as per-pound prices. That unit-confusion warning is real operational context absent from the structured fields, though it says nothing about freshness, update cadence, or availability limits.

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 tight sentences: the return payload is front-loaded, followed by the scope disclaimers and the unit caveat. Every sentence carries distinct information and none restate the name or annotations.

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, the description is not obliged to explain return values, yet it helpfully previews them; safety behavior is covered by annotations. The remaining gap is relational — it does not distinguish itself from sibling tools like get_latest_prices or get_market_report, leaving the agent to infer which price source to pick.

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 there is no parameter semantics to document and the baseline is 4. The description adds no contradictory or redundant parameter information.

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 the reviewed USDA Texas Weekly Cattle Auction Summary) and enumerates the payload it carries — reporting period, quote units, classes, weights, source link. It explicitly disclaims what it is not (not a San Angelo benchmark, not another auction barn, not a local-area price), which lets an agent separate it from lookalike price sources without opening a 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 negative scoping ('not a San Angelo cattle benchmark, another auction barn, or a local-area price') tells the agent the context in which this tool is the right choice, and the per-head/per-pound warning tells it how to interpret results. It stops short of explicitly routing to named alternatives such as get_latest_prices or get_market_report, so there is no positive when-to-prefer-this statement.

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