memo_consolidate

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

Even with annotations declaring readOnlyHint and destructiveHint, the description adds substantial context: it details the AdvancedConsolidator algorithm, sampling behavior, budget-derived defaults, response size calculations, and the middleware refusal rather than truncation. This far exceeds what the annotations alone 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 front-loads the purpose in the first two sentences, then follows with a logically organized explanation of algorithm, parameters, and budget. It is verbose, but every sentence carries useful information, so the length is justified.

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 the output schema exists and annotations cover safety, the description completes the picture: it explains the algorithm, parameter trade-offs, default rationale, and failure behavior (budget middleware refusing overruns). No critical context appears missing.

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 input schema already has 100% description coverage, but the tool description adds non-obvious rationale: why defaults are 10x2, the token budget math, and that two sample members are enough to see a duplicate. These insights go well beyond the schema's per-parameter descriptions.

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 first sentence, 'Detect near-duplicate clusters and propose merges,' is a specific verb+resource statement that clearly defines the tool's function. It also immediately clarifies the read-only nature, distinguishing it from any actual merge-execution tool.

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 states 'Read-only — returns proposals without modifying the corpus,' providing clear context for when to use the tool. It does not explicitly name an alternative for actually performing merges, but the read-only framing makes the intended use case clear.

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