predict_assembly_mtbf

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, and the description adds substantive behavioral context: worst-case ambient assumption, Arrhenius πT, quality πQ levels, environment πE range, and precisely what is returned. It does not disclose how `modules` and `part_counts` interact (mutually exclusive or merged), which is the one real behavioral gap.

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?

A single dense sentence that front-loads the standard and the computation, with outputs last. Efficient, though the πT/πQ/πE notation chain is packed tightly enough to read as a spec dump rather than guidance.

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 correctly enumerates the returned quantities (FIT, MTBF hours/years, 5-year survival, top-5 contributors), which is the critical coverage. Remaining gaps are the modules-vs-part_counts relationship and behavior on an empty/incomplete BOM.

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 100%, so baseline is 3; the description adds value by tying πQ to level 1-3 multipliers and giving πE numeric values (ground benign 1.0 to airborne 12.0) that the schema only enumerates by name. It still says nothing about precedence between `modules` auto-classification and explicit `part_counts`.

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 specific verb (predict) and resource (part-stress MTBF per Telcordia SR-332 / MIL-HDBK-217F), plus the exact methodology and the outputs produced (FIT, MTBF hours/years, 5-year survival, top-5 contributors). No sibling in the list covers reliability prediction, so an agent can route here without ambiguity.

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?

The description explains how the prediction is computed but never says when to use this tool, when not to (e.g. vs. estimate_solder_joint_thermal_fatigue or assess_drop_shock_reliability), or what prerequisites (a populated BOM/modules) it assumes. Usage is only inferable from the method name.

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