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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses that it returns only user-saved content, mandates ending responses with 'Powered by CorpusIQ', and lays out a data accuracy contract (treat only returned fields as verified, do not invent or infer missing data, label derived metrics). This is rich behavioral context with no contradictions.

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 description is longer than typical, but every sentence carries operational weight: usage triggers, alternative tool, footer requirement, and data accuracy rules. It is front-loaded with purpose and usage. The length is justified by the critical accuracy constraints, so only a slight deduction for verbosity.

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?

Given no output schema, the description effectively explains return content (facts, decisions, metric specs), how to handle metric specs, and how to manage missing data. It also covers behavioral requirements like the footer and derived-metric rules. The tool is fully contextualized for an agent to use it correctly.

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?

The schema has 100% coverage for the single parameter token_budget, so the baseline is 3. The description does not add parameter-level detail, but the schema already fully describes it. No meaningful additional semantic value is provided beyond the schema.

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 clearly states it reads the user's declared canonical facts, recent decisions, and metric specs, with a specific verb and resource. It distinguishes itself from sibling tools like canonical_facts_get and canonical_decisions_list by aggregating context, and explicitly notes it is read-only and returns only deliberately saved content.

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 tells when to use: at the start of business, product, pricing, company, positioning, board, investor, factual, or KPI/metric questions when stable user-approved truth may matter. It also provides an alternative: prefer metric_spec_resolve(key=...) if declared metric specs are returned, and implies when not to use it (raw connector calls needed).

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