changes_since

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

readOnlyHint=true already tells the agent this is a safe read, so the description owes context instead: whether results are paginated, what the default 50 limit means for truncation, whether comments inflate payload size, or whether 'who' implies expanded user objects. None of that is disclosed; 'fields, comments, who' gestures at output shape without explaining cost or completeness.

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 short and front-loaded, so nothing is wasted. However, the compression crosses into under-specification — the colon-and-noun-list style reads like an internal note rather than an instruction an agent can act on confidently.

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?

A four-parameter read tool with no output schema and no annotations beyond readOnlyHint needs the description to explain result shape and pagination/limit behavior — the exact things left unexplained. Half the parameters are undocumented in the schema, and the description does not compensate, so an agent must guess at request and response semantics.

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 50%: 'since' is well documented in the schema and the description only restates it, while 'limit', 'workspace', and 'projectIdentifiers' carry little or no schema description and get no help from the description either. Scope behavior for the project default ('all projects') is only in the schema, so the description adds essentially nothing.

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 fragment 'Issues/PRs changed since a time' does name the resources (issues and PRs) and the temporal filter, which is more than the bare name gives. But the trailing 'fields, comments, who' is telegraphic — it is not clear whether those are return contents, filters, or opt-in expansions, so the agent cannot fully tell what the call yields versus, say, get_activity.

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?

There is no when-to-use or when-not-to-use guidance. With siblings like get_activity and undo_changes in the catalog, the agent gets no signal about which to pick for a time-window change query; the description only implies usage via 'since a time'.

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