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

Annotations already declare readOnlyHint=true, so the safety profile is covered and the description need only add context. 'Sub-5ms' and 'replaces external read tools' add a performance and substitution hint, but nothing about result limits, ranking behavior, or what the format modes produce.

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 short sentences with no padding and the capability claim front-loaded. The brevity comes at the cost of specificity, but nothing is redundant or buried.

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?

For a read tool with full schema coverage and readOnly annotation, the description is minimally sufficient. However, with no output schema, an agent has no idea what a recall result looks like, what 'ribbon' returns, or how depth changes the result, which the description should have addressed.

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 each of the four parameters is already documented in the schema, including depth, format, and space_id. The description adds no further meaning, and the unexplained 'ribbon' format in particular receives no elaboration beyond the schema text.

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?

It conveys a semantic-recall tool spanning tools, repos, issues and memory, but the core verb is buried under undefined jargon ('Voronoi topological walk'), which tells an agent nothing actionable. It also fails to distinguish itself from sibling recall tools such as icx_recall_scoped or icx_search_facts.

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 only usage signal is the claim 'Replaces external read tools', which gives no concrete trigger, no prerequisites, and no exclusions. It never says when to prefer this over icx_recall_scoped, icx_search_facts, or icx_multihop_walk, all of which sit in the sibling list.

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