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

Annotations already cover safety (readOnlyHint=true, openWorldHint=true), yet the description adds real behavioral context: the exact endpoint, 0.001 credits per call, and that it works without credentials up to 25 calls/day per address. That is meaningful rate-limit and auth metadata an agent can plan around, though it omits error/pagination behavior.

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?

One sentence, front-loaded with the metric being returned, followed by endpoint, cost, and quota in a compact parenthetical. Nothing is padded, though the terse parentheses style is dense rather than structured.

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 a single optional parameter, the description gives enough to make the call (cost, quota, endpoint) but leaves the one input's meaning and the composition of the returned percentile unexplained. Adequate for invocation, thin for interpretation.

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 0% for history_years, so the description carries the burden and fails: it never explains what the parameter controls or what the resulting percentile is computed over. The max of 100 and default of 5 are only visible in the schema, leaving the unit and effect of history_years opaque.

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 identifies the resource (Shiller PE valuation with a historical percentile) clearly enough that an agent knows it returns a valuation indicator, and it distinguishes itself from indicators_buffett by the metric named. However, the text is essentially the title restated plus endpoint metadata, with no verb or explanation of what the returned percentile represents.

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 guidance on when to prefer this indicator over siblings such as indicators_buffett or intrinsic_value, and no stated prerequisites beyond implicit auth. The credit cost and 25-call/day unauthenticated limit are operational facts, not usage guidance for choosing the tool.

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