edge_metrics

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

Annotations declare readOnlyHint:true and idempotentHint:true, and the description builds on this with rich behavioral detail: level auto-estimation from first/last 10% of window (not global min/max to avoid overshoot contamination), sub-sample-accurate linear interpolation for crossings, and rejection of AC analysis. It also discloses the default-first-edge behavior and its pitfall (power-up artifact). This is exactly the kind of context that annotations cannot convey.

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 impeccably structured: purpose, returns, behavioral details, a CAPS-emphasized warning ('PICK THE WINDOW'), and a closing sentence on alternatives. Every paragraph earns its place. A minor deduction because it could arguably be tightened, but the all-caps callout and logical flow make it worth the length.

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?

For a tool with 14 parameters, an output schema, and 47 siblings, the description is remarkably complete. It covers purpose, return values (transition_time, slew_rate, levels, crossing times), key behavioral nuances, parameter selection guidance for edge cases, and explicit alternatives. The presence of an output schema means return-value details need not be repeated, and the description wisely focuses on decision-relevant information.

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% with individual parameter descriptions (e.g., t_start explains the startup-glitch recommendation), so baseline is 3. The description adds value beyond the schema by explaining the semantics linking low_pct/high_pct, the window parameters, and edge_index to real usage intent ('Use edge_index only when multiple edges in the window are intentional'). It doesn't fully cover all 14 parameters (e.g., job_id, format), but the schema already documents these well.

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 + resource pairing: 'quantify HOW FAST one transition happened: rise time, fall time, slew rate.' It clearly distinguishes itself from siblings by explicitly naming alternatives: 'For settling/overshoot after the edge, use pulse_response. For delay between two signals' edges, use timing_between.' This meets the highest bar for purpose clarity.

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 states when to use ('Use when you need to quantify HOW FAST one transition happened'), provides a clear exclusion ('Rejects AC analysis'), gives detailed situational guidance ('If the transient has startup glitches or multiple edges, set t_start/t_end tightly around the edge you care about'), and names specific alternatives with their use cases (pulse_response for settling, timing_between for delay). This is model usage guidance.

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