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

With no annotations, the description does real work: it discloses that the delta envelope is signed, that each new row carries its source page, and that payment settles on x402 inside the call — a significant behavioral and cost trait. However, it omits permission/auth requirements, behavior when 'since' is empty, and whether issuer+market together is an error.

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 leading question front-loads the intent well and every clause carries information (scope, market enum, signing, payment, facts-level opening). The second sentence is a dense run-on of em-dash and middot-separated fragments that takes effort to parse, which costs a point.

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?

Given a 3-parameter tool with an output schema, the description covers scope, the market enumeration missing from the schema, response shape at a high level, and the payment mechanism. The remaining gap is edge-case behavior (empty 'since', conflicting issuer/market), which is minor but non-trivial for a paid call.

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 carry all three parameters, and it does explain 'since' (instant or date of last read), 'issuer' (single issuer scope) and 'market' (with the full allowed value list, absent from the schema, plus the 'no issuer' condition). It stops short of stating defaults — e.g. what an empty 'since' returns — so compensation is strong but incomplete.

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 framing question 'What has this issuer filed or released since my last read?' states the resource (filings/releases) and the delta-since-timestamp scope specifically. It is distinguishable from get_issuer and list_filings by its incremental nature, though the operative verb is implied rather than stated outright.

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 tells the caller what to pass (the instant/date of last read) and gives two usage modes: one issuer, or a whole market with no issuer. What is missing is routing guidance — when to prefer this over list_filings or get_issuer — and what happens on a first read with no prior instant.

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