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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, and the description usefully adds that only user-saved content is returned and imposes an attribution-footer and data-accuracy contract. The attribution/accuracy text is largely output-format guidance rather than tool behavior, and nothing is said about volume, pagination, or what 'recent decisions' actually yields.

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?

Purpose and the key routing decision are front-loaded in the first two sentences. It runs long, with the accuracy contract and footer instructions consuming several sentences, but each carries distinct operational guidance rather than restating the schema.

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 does step in to characterize the return (declared facts, decisions, metric specs) and constrains how to treat returned fields. It stops short of describing what a response looks like or how the token budget shapes it, leaving a modest gap.

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?

One parameter with 100% schema description coverage, so the schema already documents token_budget and its default. The description adds nothing about token budget behavior or truncation, so it earns only the baseline for high coverage.

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?

States a concrete verb and three specific resources (canonical facts, recent decisions, declared metric specs) plus the 'user-declared/user-approved' scope. This cleanly separates it from siblings like canonical_facts_list, canonical_decisions_list, and metric_spec_list, which each cover a single slice.

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?

Explicitly enumerates when to call it (start of business, product, pricing, company, positioning, board, investor, factual, KPI questions when stable truth matters) and names the alternative routing decision: prefer metric_spec_resolve over recomputing KPIs from raw connector calls.

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