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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds context beyond that: it states the response includes both filing-date and realtime price blocks, that the realtime block returns a hint when current_price is omitted, and discloses credits (148) and the exact endpoint (POST /api/v1/metric/all). This gives an agent a clear model of what happens on invocation without contradicting annotations.

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 long but densely packed; it front-loads the core purpose and then methodically covers distinctions, response behavior, prerequisites, and each optional parameter with constraints. While it could be tightened, every sentence carries useful information and the structure is logical. It earns a 4 rather than a 5 because of its length, though it is not verbose.

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?

Despite the tool having 7 parameters and many siblings, the description covers the critical context: what the tool returns, how to obtain the required metric_group_id, cost, endpoint, plan requirements, and parameter-specific behavior. Since there is no output schema, the description also gives a useful note about response composition (both price blocks and the hint behavior). It leaves no obvious gap an agent would need to resolve before calling 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?

Schema coverage is 100%, so the baseline is 3, but the description adds value by explaining the purpose and behavior of parameters beyond their schema descriptions. For example, it explains that current_price is 'supply to compute realtime price-sensitive ratios' and that omitting it 'receive a hint instead', and that light_weight_mode is meant to 'strip per-metric audit fields to reduce payload size'. It also frames formula_override as 'for user-formula metrics (per API rules)', which is helpful context not found in the schema alone.

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 opens with a specific verb and resource: 'Return the full metrics bundle for one metric_group_id' and clarifies it covers 'all computed ratios and line-backed metrics for that filing-period snapshot.' It clearly differentiates from siblings by stating these are 'precomputed metrics, not XBRL facts' and explicitly names query_line_items and get_filing_facts as the alternative for line-item values, plus get_metrics_bundle_filing_date for filing-date-only needs.

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 explicit when-to-use and when-not-to-use guidance: directs users to call list_metric_snapshots first to obtain metric_group_id, tells them to use query_line_items or get_filing_facts for line-item values, and says to call get_metrics_bundle_filing_date if only the filing-date computation is needed. It also includes plan-level prerequisites (Starter or higher, Pro+ for formula_override) which helps an agent decide if it can invoke it.

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