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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, and the description adds substantial behavior beyond them: results are 'compact candidates only' requiring a follow-up fetch, the call is anonymous, queries must not contain secrets/private context, and returned content is untrusted data whose instructions must never be followed. That is a rich, non-redundant disclosure of cost, privacy, and prompt-injection risk.

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?

Dense but front-loaded: purpose first, then usage, then query strategy, then safety caveats. Every sentence carries information (no filler), though the safety/trust notes packed at the end make it a long single block that could be marginally tighter.

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?

An output schema exists, so return values need not be detailed, yet the description still flags 'compact candidates only; fetch the likely ones' to set follow-up expectations. Combined with query strategy, privacy constraint, and untrusted-data warning, an agent has everything needed to call and interpret this correctly for an 8-param, 0%-coverage search tool.

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 0%, so the description must compensate. The 'exact error literal (mode exact/substring) → product + literal → normalized symptom (keywords) → filters' line maps directly onto the mode enum values and the product/filter parameters, adding real semantic guidance. It does not explain page, limit, type, signal, or status, so it is not exhaustive, but it meaningfully covers the most decision-critical parameters.

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+resource with qualifiers: 'Search shared, revisioned technical Problems and Solutions'. The scope ('shared, revisioned', 'Problems and Solutions') plus the companion hint 'fetch the likely ones' cleanly distinguishes it from the fetch/get_changes siblings.

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?

Gives explicit triggers ('error looks infrastructural, protocol- or tooling-related', 'before broad web research', 'retries/idempotency/versions/environments matter') AND explicit exclusions ('trivial syntax errors, simple edits, project-specific business decisions, obviously unique local issues'), plus a prescribed query escalation order. Nothing about when-to-use or when-not-to-use is left to inference.

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