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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description usefully goes beyond them by spelling out the exact shape of each returned row (record, kind, field, old/new value, claim, evidence URL, data commit) and the timestamp normalisation rule. It omits ordering and pagination behavior, which keeps it short of a 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?

Two tight sentences, front-loaded with the purpose, then inputs, then outputs – no filler. It is dense but readable, and every clause carries information. The compressed 'Input:'/'Returns:' phrasing is efficient rather than padded.

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 rightly documents the returned row, and it covers the required argument's format. But for a 4-parameter tool it leaves step, record_id and limit semantically undefined and says nothing about result ordering, truncation, or how far back it scans, which are the questions an agent still has before calling it.

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 only 25% – solely 'since' is documented in the schema – so the description is expected to compensate but mostly does not. It restates 'since' as an ISO date (slightly at odds with the schema's 'offset is applied, then the UTC date is used') and merely names step, record_id and limit without explaining what each filters or how limit bounds results (schema caps it at 200 but the description doesn't say it truncates).

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 opening sentence names a concrete resource and action ('what changed on the map since a date'), which is far clearer than the bare tool name 'changes'. It also enumerates the returned row fields, reinforcing what the tool produces. It does not, however, distinguish itself from near-neighbors like 'stale' or 'search', which an agent may reasonably confuse it with.

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 by the purpose sentence; there is no explicit statement of when to pick this over 'stale', 'search', or 'get', and no prerequisites or exclusions. The optional filters (step, record_id, limit) are listed but never framed as selection criteria for a scenario.

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