Widget-storage residue verdict

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

With no annotations, the description carries full burden; it does disclose that clear:true triggers a clearing action with a re-read-verified signed receipt, which is meaningful behavioral context. However, it never states whether clearing is destructive/irreversible, what permissions are required, or what the census returns, and the unexplained '$4.99' pricing is ambiguous noise rather than a clear cost disclosure.

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?

It is technically short, but it is a single dense clause packed with undefined jargon and an out-of-place price tag, so it fails to front-load the plain purpose. The '$4.99' fragment distracts rather than earns its place.

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?

With no annotations, no output schema, and 0% schema coverage on a 3-parameter tool, the description should carry far more. It mentions the receipt behavior but omits parameter semantics, destructiveness, and return shape, leaving an agent unable to invoke it reliably.

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 document all three parameters; it only meaningfully explains 'clear:true' (adds a receipt). 'host' and 'server_id' are never clarified — their format, uniqueness, and role in the 'server x host origin' pairing are left entirely to inference.

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?

"Residue census" plus a "hash-only census per server x host origin" implies a storage-scanning/enumeration tool, but the core resource being censused is never plainly stated, and the jargon ('residue', 'verified-clear receipt') forces the agent to guess. It does not differentiate itself from siblings storage_matrix or storage_probe at all.

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?

There is no statement of when to use this versus storage_matrix or storage_probe, and no prerequisites or exclusions. The only usage hint is the conditional 'clear:true adds the ... receipt', which explains a mode but not when to choose this tool.

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

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

With no annotations, the description carries full behavioral burden, yet it only discloses a cost ($3.99) and a vague 'watch allowance applies' constraint. It never says whether the call is read-only, whether it has side effects, how long the 5-host sweep takes, or what happens on partial failure.

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?

It is a single short sentence with the scope front-loaded, so there is little waste. However, the jargon ('watch allowance applies', 'widget x hosts') makes the content opaque rather than concise.

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 tool with a nested required object, zero schema documentation, no annotations, and no output schema, the description is far too thin. An agent cannot construct a valid 'widget' argument or predict the return structure from this text alone.

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% and the required 'widget' parameter is a nested object of undocumented structure; 'server_id' is likewise unexplained. The phrase '1 widget' offers no additional meaning about what a widget is or what server_id scopes, so the description does nothing to compensate for the coverage gap.

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 mostly restates the tool name ('Full storage matrix') and never states a verb or action, so it is unclear whether this retrieves, computes, or builds anything. It does add scope ('1 widget x 5 hosts with per-host verdicts'), which hints at the shape of the result, but the operational purpose remains undetermined.

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?

No indication of when to use this over the sibling tools storage_census or storage_probe, and no prerequisites or exclusions are given. The only guidance is a price, which does not help an agent choose the right tool.

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

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: this performs a real write attempt, has real cost, and has a per-operator trial limit. What it omits is what exactly gets written, whether anything is cleaned up, and how failures other than 'forbidden-throws' manifest.

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?

It is a single dense sentence with no filler and the key scoping phrase ('single widget x host') is front-loaded. The machine-like slash-delimited jargon and unexplained all-caps labels cost readability, so it is compact but not optimally structured.

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 tool with non-trivial write behavior, zero annotation coverage, 0% parameter documentation, a nested object parameter, and no output schema, the description does too little: it never explains server_id, the widget payload, or the shape of the returned grading. The three outcome labels hint at return values but are not defined.

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% across three required parameters, and the description only maps to two of them ('widget' and 'host'), leaving server_id entirely undocumented. It adds no detail on the shape or content of the nested widget object that the agent must supply.

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 identifies a storage probe scoped to a single widget x host and names the three outcome classifications it produces, so the resource and action are discernible. However, it never distinguishes itself from siblings storage_census and storage_matrix, and the telegraphic jargon ('PERSISTS-KEYED / EPHEMERAL / FORBIDDEN-THROWS') leaves the actual purpose partially opaque.

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 guidance given is commercial (costs $0.99, one free trial per operator ever), which signals a constraint but not when to choose this tool over storage_census or storage_matrix. There is no stated condition for use, no prerequisites, and no exclusion criteria.

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