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

Annotations already cover the read-only/idempotent/closed-world profile, and the description goes well beyond them: it defines the share metric, gives the exact 45% threshold for possible_repeat, supplies empirical calibration (13 of 21 paragraphs flagged, 0 of 4 unrelated passages), and explicitly frames the signal as word overlap rather than a judgement of coverage. That framing is exactly the kind of caveat an agent needs to avoid over-interpreting results.

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?

Front-loaded with purpose, then metric definition, then the kind grouping. Dense and mostly earning its place, though the empirical validation figures and the closing boilerplate about retrieval not certifying truth add length that could be trimmed.

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 carries the full burden of explaining return shape and does so: results grouped by kind, each with URL and share, plus the possible_repeat flag semantics. An agent knows what it will get and how to read it before calling.

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 both parameters are already documented, including the per-kind defaults and the 'does not open links' constraint on `text`. The description adds no syntax, format, or sizing guidance beyond the schema, so baseline 3 applies.

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 (compare a passage) and resource (the whole archive) and names exactly what comes back: grouped essays, ledger claims, weekly calls, laws, tools and models with URL plus a share score. It is clearly not a plain keyword lookup, but it never names or contrasts the sibling `search` tool, so the boundary with that tool is left to inference.

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 use case (checking whether a passage already exists in the archive) is implied by 'compare ... with the whole archive' and by the possible_repeat explanation, and the closing caveat warns against treating results as coverage proof. But there is no explicit when-to-use, when-not-to-use, or 'use `search` for X instead' routing statement.

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