land_projects_history

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

With no annotations, the description carries the full burden. It discloses several non-obvious behaviors: the offset quirk (offset did not reach later rows in probes), the local limits (100 rows, 256 KB) and that the response reports the bound if cut, the possible extra verified deed GET with a two-request limit, and that resolved results include plot identities and freshness. These go beyond a simple 'list records' and are valuable for the agent to set expectations. It does not mention side effects (none expected) or authentication, but the disclosed behaviors are substantial.

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 description is longer than necessary, including a detailed account of probe history ('The recorded history probes were a bare request, offset=1, limit=2...'). While this information is relevant, it could be condensed to 'offset may not behave as expected; limit works.' The core purpose is front-loaded, but the middle section is dense and could be streamlined. It is not excessively verbose, but it lacks the crispness of the best examples.

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?

The description covers many aspects: purpose, parameters, bounds, and extra requests. However, it does not describe the output structure. With no output schema, the agent is left guessing what fields a 'land project record' contains. It does hint at some fields (plot identities, freshness) but not the full record. Given the complexity of the tool (4 parameters, no required ones, no output schema), the description is fairly complete on behavior but incomplete on the return format, which is a notable 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?

Schema coverage is 0%, so the description must compensate. It clarifies that exactly one of plot_id or deed_uid must be supplied, and explains acceptable formats: plot_id can be numeric or display label, deed_uid is a string, and 'original UID spelling is also accepted.' It also gives behavioral hints about limit (narrowed from start) and offset (did not reach later rows), which helps the agent understand their effect. It does not explicitly define the meaning of limit/offset beyond the quirk, but it provides enough guidance for correct invocation.

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 first sentence states the core action: 'List the land project records the upstream returns for one deed uid.' This is a clear verb+resource and specifies the scope (one deed uid). It distinguishes from sibling tools like land_projects_count and land_projects_active, though it doesn't explicitly contrast with all of them. The phrasing 'the upstream returns' is slightly indirect but understandable. Overall, purpose is clear and specific.

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 provides usage context: it says to supply exactly one plot_id or deed_uid, which is essential. It references the sibling land_projects_count and notes that its count may not match this tool's results, giving a clear alternative. It also mentions the server-side bounds (100 rows, 256 KB) which affect usage. However, it does not explicitly exclude other related tools (e.g., land_projects_active) or state when to choose this over them, so it's not exhaustive.

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