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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavior context by revealing the output is a plain-language verdict rather than raw data, but it says nothing about invalid-slug handling or whether the two inputs must be the same entity type.

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?

Two tight sentences: the first defines the operation and output, the second gives the usage timing. Nothing is redundant and the essential information is front-loaded.

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 appropriately characterizes the return value as a verdict; with two fully undocumented required parameters, it supplies their semantic form (slugs). The remaining gap is error/mismatch behavior, which is minor for a read-only two-slug comparison.

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 0%: 'a' and 'b' are bare strings with only length constraints, so the description must carry the meaning. It does partially compensate by stating inputs are slugs referencing schools, apps or tutors, but it never maps a/b to first/second option, nor does it require the two to be the same entity type.

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 (side-by-side comparison) and resource (two schools/apps/tutors) plus the input form (by slug) and output form (plain-language verdict). It is clearly distinguishable from siblings like tdd_search or tdd_shortlist, which surface candidates rather than judging two of them.

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 says when to use it: 'after a search or shortlist when someone is choosing between two,' which ties it to the search/shortlist workflow. It stops short of naming when NOT to use it (e.g., comparing more than two, or comparing a mix of entity types), so it is clear context without exclusions.

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