Landosaur

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious context: output preserves source evidence and price basis, and the result must not be read as an appraisal, title opinion, or buildability guarantee — useful framing for how an agent should present results. It does not say how invalid or duplicate IDs are handled.

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 verb and cardinality, then the interpretive caveat. Nothing is padded and every clause carries 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?

With no output schema, the description carries the return-shape burden and does note that source evidence and price basis are preserved. It is adequate for a single-parameter read-only tool, though it leaves the result structure and error behavior 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 description coverage is 0%, so the description must carry the meaning of `ids`. It partially does by tying the input count to 'two to five public listings', matching the minItems/maxItems, but it never says where to obtain those IDs (search_land is the obvious source) or that the pattern restricts the identifier format.

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+resource (compare land listings) and adds an explicit cardinality bound, which distinguishes it from the singular get_land_listing sibling. It stops short of naming siblings by name, so an agent must infer the split from the verbs alone.

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 2-5 bound implies usage, but there is no explicit routing guidance: nothing says to call search_land first to obtain IDs, or to use get_land_listing instead when only one listing is needed. The second sentence is a liability disclaimer (not an appraisal, title opinion, or buildability guarantee) rather than a when-to-use rule.

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 readOnly/idempotent/non-destructive/closed-world, so the description's marginal value is what it adds: the return contents (evidence with documented/claimed/unknown/conflicting statuses) and a data-freshness caveat that availability must be confirmed with the source. That freshness warning is real operational context not present in 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?

Three short sentences, front-loaded with the core action, then scope limits, then the freshness caveat. No filler, though the final caveat is slightly vague about what 'confirmed with the source' means operationally.

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?

No output schema, so the description does some work describing returned evidence statuses and unavailable record types. For a one-parameter read tool with full annotation coverage this is largely sufficient; only the provenance of the `id` value is left unexplained.

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% and the single required `id` parameter has no schema description at all; the description only implies the id selects a listing, without saying whether it is an internal listing id, where to obtain it (e.g., from search_land results), or its allowed character format. Contextual inference is possible but the description does not compensate for the coverage gap.

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 — 'Read one public land listing' — plus the evidence categories returned (documented, claimed, unknown, conflicting). The singular 'one' implicitly separates it from search_land and compare_land_listings, though no sibling is named outright.

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 exclusions: private drafts, rejected listings and demo data are unavailable, which prevents futile lookups. It stops short of routing the agent to search_land for discovery or to compare_land_listings for multi-record comparison, so the alternative-selection guidance is implied rather than explicit.

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 readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds a genuinely useful semantic caveat ('a listed source does not prove nationwide or complete coverage'), but says nothing about pagination limits, page bounds, 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?

Three sentences, front-loaded with the core purpose, followed by the filter/pagination note and the coverage caveat. No filler and every sentence carries 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?

No output schema, but the description characterizes the return payload (coverage plus counts of fresh available non-demo listings) and warns about interpretation. For a simple two-parameter read tool, that is close to complete; only pagination/return-shape specifics are 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 description coverage is 0%, so the description must compensate. It does map both parameters ('supports a state filter and pagination'), but adds no detail on state format (the schema regex handles that), page bounds (max 10000 in schema), or default pagination behavior.

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: 'Read public land-source coverage and counts of fresh available non-demo listings.' Clearly a coverage/inventory read, distinct from the listing-oriented siblings (search_land, get_land_listing, compare_land_listings). It does not explicitly name or contrast a sibling, so it stops 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?

Usage is only implied — an agent infers this is the source-coverage/inventory read rather than a listing search. There is no explicit when-to-use/when-not or pointer to a sibling like search_land for actual listings.

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 the safety profile is covered. The description adds behavior the schema does not: an implicit seven-day observation window on the default availability and a cash default for price filtering, both of which materially change results and are not encoded anywhere in the schema.

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 tight sentences, purpose front-loaded followed by the defaults an agent would otherwise get wrong. No filler, though the second sentence compresses three separate default behaviors into one clause and could be split for scannability.

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 an 11-parameter read-only search with no output schema, the description supplies the critical defaults and hints at return content (source links, price basis, observation dates). Gaps remain around pagination/result limits and what 'non-demo' actually excludes, but nothing essential to issuing a correct call 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 description coverage is 0% across 11 parameters, so the description carries the burden. It explains the two most ambiguous ones well (priceKind defaults to cash; availability defaults to recent observations), but leaves sort values like 'evidence', 'recommended' and 'acre_price' and the availability enum members 'historical'/'unconfirmed' undefined, so compensation is 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 verb and resource ('Search public, non-demo land listings') plus the payload an agent can expect (source links, price basis, observation dates). Siblings (get_land_listing, compare_land_listings, read_source_coverage) are distinct enough by name that no explicit routing sentence is strictly needed, but none is offered.

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 conveys the default search context ('available listings observed within seven days') and steers the agent to set priceKind explicitly when comparing non-cash prices. However, it never names an alternative tool or says when to prefer get_land_listing or compare_land_listings over this one, so usage is implied rather than stated.

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