pit_changes

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

With no annotations the description carries the full behavioral burden. It discloses the auth requirement, the column structure, the incremental cursor (`through`), and explicit limits on what it does (no comparison, no causal explanation), which is solid. It still omits rate limits, pagination/volume expectations, and error behavior for an unannotated data-feed tool.

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 purpose is front-loaded ('The daily update...'), and the sentences carry distinct payloads: column shape, `restated` semantics, cursor handoff, auth, and limits. The long first sentence with an embedded parenthetical is dense but not wasteful.

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 and no annotations, the description does substantial work: it defines the returned column shape (parity with point_in_time plus `restated`), the cursor contract, and negative capability limits. What remains missing is volume/rate/error context, but for a one-parameter feed tool it is close to callable.

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 100% and there is a single required parameter, so the schema already documents `since` fully. The description's `through`-as-next-`since` line reinforces the cursor loop but largely restates what the schema text says. Baseline 3 for high-coverage schemas is appropriate.

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?

It states a specific resource and scope: a daily delta feed of every row filed after `since` across all filers, with column parity to point_in_time plus `restated`. The `stre restated` semantics are defined inline. It stops short of explicitly contrasting itself with the siblings (recasts_free, check_claims), so it is clear but not fully differentiated by name.

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 usage pattern is spelled out: pull daily, then feed `through` back as the next `since`, and it notes the auth prerequisite (STOCKONOMY_API_KEY). It also states a limitation ('compares nothing and does not say why a value changed'), which functions as a when-not-to-use signal, but no alternative sibling is named for the 'why did it change' case.

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