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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes far beyond them: it discloses that seeded rows are excluded so history never reads as this week, describes entitlement truncation (first 5 rows plus locked.count and locked.by_type), and states that contact values and decision-maker names are never returned. This is rich behavioral context an agent could not get from the structured fields.

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 purpose is front-loaded, but the middle is an over-long run-on enumeration of change types (commitments, allocation targets, consultants, borrowers/lenders, markdowns, maturities, etc.) that could be trimmed. The closing promotional line ('7 days free at https://dfxintel.com/...') is not functional content and dilutes an otherwise informative description.

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 reasonably: it explains that every answer reports what it withheld via entitlement and locked, and that list responses degrade to counts by type. A few schema gaps (event_type, limit) remain, but the critical behavioral contract is covered.

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%, so graph and since are already documented. The description adds meaning for include_seeded (explaining 'seeded when the arm was created' as history vs this week) and references next_since for polling, but leaves limit and event_type undescribed. This is marginal value over the schema, consistent with the baseline.

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 description states a specific resource (the change tape across the allocator, private credit and real estate fund graphs) and a distinctive ordering principle (FIRST SIGHT, the day DFX first saw each row). It enumerates the kinds of changes captured, so an agent can tell what it returns. However, it never names or contrasts with close siblings like changes_since or search_private_credit_changes, so differentiation must be inferred.

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 one concrete usage instruction — 'Poll with the next_since the answer returns' — and explains the access-tier behavior. But it offers no explicit when-to-use/when-not guidance relative to the many sibling change/search tools, leaving selection to inference.

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