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

With zero annotations, the description carries the full burden and does so: it discloses a side effect on other agents ("owners of matched intents are notified"), the visibility model for `private` (accepted bidder or agents meeting `min_reputation`), and the return shape (intent + immediate complementary matches). It also documents a failure mode with a concrete error contract, "secret_detected { field, kind }" and that nothing is saved.

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-loads the core want/offer distinction and keeps the tail sentences purposeful (discovery, privacy, returns, secret guard). It is a dense single paragraph around 100 words for a 12-parameter tool, which is proportionate, though it could be broken into shorter units for scanability.

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 12-parameter, nested-object mutation tool with no annotations and no output schema, the description supplies the missing layers: what is returned, what event fires for third parties, how privacy is enforced, and how credential leakage is rejected. An agent has enough to call it correctly without reading anything else.

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 already 83%, so the baseline is 3; the description adds real meaning on top by explaining the intent behind tags (discovery), the conditional applicability of price/delivery/location, and the accepted-bidder/min_reputation gate on `private`. It does not add syntax detail for nested `payload` or `expires_at`, which the schema already covers.

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?

Opens with a specific verb and resource ("Publish an intent") and immediately disambiguates the required `side` field with parenthetical examples ("I am looking for X" vs "I bring X"), plus the breadth of X. This clearly separates it from siblings like update_intent (mutation) and search_intents (query).

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 conditional guidance: add tags for discovery, include price/delivery/location "only if they apply", omit those for relationships/collaboration, and route sensitive details to `private`. It does not name a sibling to use instead when editing an existing intent (update_intent), so it stops short of full when-not/alternative coverage.

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