ParcelSheet

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely non-obvious behavior beyond them: the returned link expires after a day and there is a hard free-tier cap of one clip per month. It does not state rendering time, latency, or failure modes, but the rate limit and link lifetime are the details an agent most needs.

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?

Four short sentences, front-loaded with the deliverable and format, then the return, then the cost. The mid-sentence visual flourish ('the lot swinging left and right with its lot line on the ground') is slightly superfluous but sets expectations about the output.

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 covers the return (an expiring download link) and the commercial limits. The one gap is that the schema marks zero required parameters, so an agent could call with neither tmk nor address; the description implies a TMK is needed but never states that at least one locator is required.

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 100%, so tmk and address are already fully documented (format, dashes optional, example address). The description only reiterates 'by TMK' and adds no syntax or alternative-parameter guidance beyond the schema, so the baseline of 3 applies.

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 concrete verb and artifact ('A looping 3D video (MP4) of one Hawaiʻi lot by TMK'), names the data source (USGS lidar) and the return type (download link). That is clearly distinguishable from the sibling tools, which return parcel data, records, or lot lists rather than a rendered video.

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 explains pricing tiers ('Free: 1 clip a month. More with ParcelSheet Pro') but never says when to choose this tool over get_parcel or search_lots, nor what prerequisites the caller needs. The only usage hint is the implied 'need a video' context, which the agent must infer.

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 cover readOnlyHint and openWorldHint, and the description adds substantial context beyond that: data provenance (USGS lidar, lot line on the ground), the breadth of findings (zoning, flood, tsunami, sea level rise, wildfire, lava), the quota limits, and the Pro paywall. Missing only auth/error behavior, so 4 rather than 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?

It is a single long sentence but front-loads the core action ('A 3D picture of one Hawaiʻi lot by TMK') before the payload and pricing details. Slightly run-on, though nearly every clause carries useful information for selection.

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 read-only lookup with no output schema, the description does the heavy lifting by describing the returned content and its sources, plus quota/pricing constraints. Nothing essential for a correct call is missing, though error and fallback behavior for invalid TMKs is 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 100%, so both tmk and address formats are already fully documented with examples in the schema. The description reinforces the TMK path but adds no syntax or constraint detail beyond what the schema provides, so the baseline 3 applies.

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 ('A 3D picture of one Hawaiʻi lot by TMK') and enumerates what the result contains, so an agent immediately knows this is a single-parcel lookup. What it does not do is explicitly distinguish itself from siblings like search_lots or get_public_records, leaving the boundary to inference.

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: it tells you to identify a parcel by TMK or address and quotes free-tier quotas (1 lot/day, 5/week), which is a real usage constraint. But there is no explicit when-to-use guidance and no direction on when to call search_lots or get_public_records 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 already cover the safety profile (readOnlyHint=true, openWorldHint=true). The description adds one genuine behavioral fact beyond them — the subscription gate — but says nothing about return volume, pagination, or coverage limits for a parcel with many permits and notices. With no output schema, more behavioral detail would help.

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, front-loaded sentences with no filler; the resource comes first and the constraint second. It is telegraphic rather than polished, 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?

For a simple read-only lookup whose schema is fully documented, the description is adequate on scope and pricing but silent on the address alternative, on whether either parameter is required, and on result size. A caller passing an address instead of a TMK gets no confirmation from the description that this is valid.

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 100%, so both tmk and address are fully documented with format examples in the schema. The description adds nothing beyond 'one TMK' and notably omits that address is an accepted alternative identifier, leaving the baseline 3.

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 resource set (county tax sale notices and building permits) scoped to a single parcel, which is concrete enough for an agent to know what comes back. However, it never contrasts itself with the siblings get_parcel, get_clip, or search_lots, so an agent must infer the distinction from the name 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?

'ParcelSheet Pro ($22 a month) only' is a real access precondition that most tools hide, but there is no explicit when-to-use versus alternatives guidance and no statement about what happens if the caller lacks the subscription. Usage is only implied from the resource description.

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 and openWorldHint=true, so safety is covered; the description adds real value beyond them by disclosing the 50-lot result cap, that each lot links to a full sheet, the default of 25, and the ParcelSheet Pro ($22/month) access requirement.

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 dense sentences: outputs and filters first, then the area input formats, then result cap and access tier. Every sentence carries distinct information and nothing is repeated from the schema.

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 exists, so the description correctly carries the return shape (up to 50 lots with acres, zoning, flood, SMA and a link to the full sheet) and the auth/pricing gate. It omits what happens when no area input is supplied, which matters given required parameters = 0.

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?

With 13 parameters at 69% schema coverage, the description clarifies the disjunctive structure of the area parameters (TMK prefix OR radius around a lot OR address OR point) and groups the filters (zoning, size, flood, SMA), which the flat schema does not convey. It still does not explain lat/lon pairing or that no parameter is actually required.

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 ("Lists") plus resource ("lots") plus scope ("in an area") and the exact fields returned (acres, county zoning, FEMA flood zone, SMA). An agent can tell this is an area-based search rather than a single-parcel getter, but no sibling (get_parcel, get_clip) is named to make the boundary 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?

The description discloses the valid area input modes (TMK prefix, radius around a lot/address/point) and the result cap, which implies how the tool is meant to be called, but it never states when to prefer this over get_parcel or get_clip, nor any exclusions or prerequisites beyond the pricing note.

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