PlaceDossier

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still adds real context beyond them: the one-lot vs many-lots behavior, nearest-first ordering, and the caveat that the open parcel map carries no lot numbers so selection must be by plan and size or on the page. It does not discuss the zero-argument case despite all parameters being optional.

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 core verb+resource and input modes, with return fields and edge-case behavior after. The final sentence is long and packs three ideas (address-vs-street behavior, plan listing, missing lot numbers), which costs some scannability but 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?

No output schema exists, yet the description names the returned fields (PID, plan, mapped area, report page), enough for an agent to know what it gets. With zero required parameters it leaves open what happens on an empty call, a minor but real gap for a 3-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?

Schema coverage is 67%, and the description compensates by spelling out the accepted query formats (civic address with town, dashed PID, legal description or plan number, including the old land-district form) and by framing lat/lon as a 'point' lookup that returns nearby lots. It does not state whether lat and lon must be supplied together.

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 (find the titled ParcelMap BC lot) and enumerates the four lookup modes: civic address, PID, plan in a legal description, and point. It also names what is returned (PID, plan, mapped area, report page) and ties the PID back to the sibling parcel_report, so an agent can separate the two without opening either 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?

Explains how each input type behaves — an exact civic address yields one lot, a street/block/point yields the surrounding lots nearest first, a plan yields all its lots — which is effectively guidance on which input to choose for which intent. The handoff to parcel_report is only parenthetical ('PID (for parcel_report)'), not an explicit 'use parcel_report instead when…' 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?

Goes well beyond the readOnly/openWorld annotations: it discloses first-call latency (10–20s), data provenance caveats (zoning is a dated summary of the bylaw), a 'not available yet' error state, and scope exclusions (no scores, valuations, or owner names). It does not describe pagination or size limits beyond the ~40 KB full flag.

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 core operation and the status legend packed into a single parenthetical, then the section list. The 27-section enumeration is long but load-bearing; the nested parenthetical makes the first sentence heavier 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 carries the return-shape burden and does so: it defines each status value, what accompanies a named section (facts, notes, sources, licences), and the default headline-only behavior. An agent has enough to call it and interpret the response.

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 is 3. The description mostly restates the schema's 'sections' semantics, though it does add one genuinely new constraint — the lake section requires a sampled lake — and defines the status vocabulary the sections return.

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 per-lot public-record report keyed by PID, with an explicit inventory of what the report contains. It implicitly complements the sibling find_parcel (which supplies the PID), but does not explicitly contrast with it inside the description itself.

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: the description notes the 10–20 second cost for an unbuilt lot and that the lake section only appears 'beside a sampled lake', which quietly steers section selection. There is no explicit 'use this when…' or named alternative beyond the PID source hint.

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