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

Annotations already declare readOnly/openWorld/non-destructive, so the bar is lower, but the description still adds real context: no API key required, works when Awareness memory is not configured, results are user-published and unvetted. The reporting rules ('do not invent capabilities', 'say Awareness does not vouch for quality') are useful behavioral constraints a caller could not infer. It stops short of describing ranking/latency or result-size limits beyond the `limit` argument.

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?

Purpose and trigger are front-loaded, and the Args/Returns blocks are scannable. The reporting-rules bullets are longer than strictly needed for tool selection, but each sentence carries usable instruction rather than filler, so the size is defensible.

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 five-parameter, zero-schema-coverage read tool with no output schema, the description covers everything an agent needs: what it does, when to use it, all parameter semantics, and an explicit return shape ('listings', 'total', 'market_url') including per-listing fields and the `url` key. Nothing material is left for the agent to guess.

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%, so the description must carry the full load and it does: it explains what `query` matches (title/summary), enumerates the `category` values, lists every valid `sort_by` value with its default, defines `price_filter` values, and gives the 1-100 range for `limit`. This is a substantial gain over bare typed properties with defaults.

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 description opens with a specific verb and resource ('Search the Agent Memory Market') and immediately qualifies the scope ('ready-made memory packs, skills and agents'). It also explicitly distinguishes itself from the sibling memory tools ('This is NOT a memory tool'), so an agent can route correctly without opening a schema.

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?

It states the triggering intent ('when the user wants to FIND AN AI AGENT or memory pack to use, install or hire') and backs it with three concrete example utterances, including a non-English one. It also gives an explicit exclusion (not a memory tool) and notes it works without configuration, which is the key precondition an agent would otherwise guess at.

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