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

Beyond the readOnly/openWorld annotations, the description discloses the key behavioral traits: it is a derived local version record rather than ISA's live files, unpublishable actions are silently omitted, departures are reported only as an anonymous count per version, and history is bounded by tracking_since with a 30-day free window. These are exactly the caveats an agent needs to interpret results correctly.

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 core question is front-loaded in the first sentence, and each subsequent sentence adds a distinct constraint (data provenance, per-change contents, exclusions, history window, free tier). The clause about counts 'that left the files per version' is dense and slightly opaque, costing a bit of clarity.

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 four parameters, an output schema and readOnly annotations, the description covers provenance, output shape (action id, observed_at, changed fields, before/after) and boundary conditions. The one soft spot is the vague handling of removed-action counts — it is unclear where in the response those numbers appear.

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 since, limit, change_type and target_type are already documented in the schema itself. The description adds only that 'since' bounds a change window; it offers no extra semantics for the enum filters or the limit default. Baseline 3 applies when the schema carries the parameter detail.

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 specific verb and resource ('Which TITP administrative actions were added to or changed') plus a scope constraint ('since a date'), which cleanly separates it from titp_action_lookup's current-state retrieval. An agent can tell this is a change-history feed over ISA's published files without opening the 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?

It gives actionable context for choosing it: history begins at tracking_since, and only the last 30 days are free. However, it never explicitly names titp_action_lookup or catalog as the alternative for current-state or single-action needs, leaving that routing to inference.

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