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

With no annotations, the description carries the full burden and does substantial work: it discloses default status=open, the stale-flag semantics, the mirrors default that changes based on whether q/tags are supplied, the pagination response fields, the api_key requirement for trusted='1', and the important guarantee that the tool never falls back to unfiltered results. Much of this duplicates schema parameter text rather than adding new behavior, but the aggregate disclosure is still strong.

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 purpose is front-loaded and the sentences are information-dense with little filler. But the single unbroken block repeats schema wording verbatim (stale, trusted, limit clamp), which adds bulk without adding meaning for a reader who already sees the schema.

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 20-parameter, unannotated tool with no output schema, the description covers the critical unknowns: defaults, pagination shape (total, total_indexed, has_more, next_offset), stale handling, and auth failure behavior. The remaining gap is that it doesn't document the interaction of lat/lng/radius_km or the sort semantics beyond what the schema says.

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 60% across 20 parameters, so the description must compensate and partially does: it explains side, stale, mirrors, trusted, limit clamping, and the geo radius filter. It says nothing about sort, lat/lng pairing, agent_id, currency, or min/max price, leaving several parameters with only their schema text, which keeps this at the baseline rather than above it.

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 opening sentence states a specific verb and resource ("Search the marketplace") and enumerates the filter surface, so an agent knows immediately this is a broad filtered-list tool. It doesn't differentiate itself from a close sibling such as find_matches or list_my_intents, which keeps it out of the top band.

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?

Guidance like "use side='offer' to find providers" and "pass stale='exclude' to hide those" tells the agent how to drive specific parameters, which is useful. However, there is no statement of when to pick this tool over find_matches or list_my_intents, so tool-level selection 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.