web3ctx

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

The readOnlyHint annotation already covers the safety profile, so the description only needs to add behavioral context. It does add one useful constraint—does not follow calls across projects—but does not disclose other behaviors like traversal direction, cycle handling, or what the returned dependency closure actually contains.

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?

Two short sentences with no filler. The core purpose is front-loaded, and the key limitation follows immediately. Every word 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?

The tool is simple in schema complexity, but there is no output schema and no parameter descriptions. The description leaves important gaps: what kinds values are accepted, how depth interacts with the closure, what the return value looks like, and which sibling should be used for cross-project scenarios. This is insufficient for fully confident invocation.

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 compensate for undocumented parameters. The phrase 'around a selector' gives some context for the selector parameter, but depth and kinds receive no explanation, and 'kinds' is especially ambiguous. The description does not materially reduce parameter misuse risk.

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 the operation as computing a dependency closure anchored around a selector, and it clarifies an important boundary: it does not follow calls across projects. This distinguishes it from generic fetch/search/lookup siblings, though the description lacks an explicit verb making the action fully explicit.

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 description implies when to use the tool: when you need dependency closure for a selector. It also gives an explicit exclusion: not for cross-project dependency traversal. It stops short of naming an alternative for cross-project cases, so it doesn't fully meet the bar for explicit alternatives.

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?

The annotation readOnlyHint already covers the read-only nature. The description adds no further behavioral details such as pagination behavior, error handling, or rate limits. It only restates the core function without additional transparency.

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 description is extremely concise, consisting of two short sentences. It conveys the essential purpose and a key constraint without any unnecessary wording, making it highly efficient.

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 output schema, the description should explain what 'full bodies' means and how the cursor works for pagination. It does not describe the return format or the interplay between selectors and cursor, leaving gaps in the complete usage context.

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?

The description does not explain the meaning or relationship of the 'selectors' and 'cursor' parameters. It does not clarify that selectors are an array of identifiers or that cursor is used for pagination, leaving the agent to infer from the schema alone.

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 clearly states the tool fetches complete units for selectors already chosen, and explicitly says it does not discover selectors. This distinguishes it from sibling tools like web3_search or web3_lookup, making its purpose unambiguous.

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 phrase 'Does not discover selectors' implicitly tells the agent to use this tool when selectors are already known, not for discovery. It provides a clear negative usage guideline, though it does not explicitly mention alternatives like search or lookup tools.

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?

The readOnlyHint annotation already covers the safety profile, and the description adds useful behavioral context: matching is exact/lexical, not semantic ranking. It does not disclose pagination, limiting behavior, or what happens when no match is found, but with the annotation covering side effects, the added value is adequate.

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?

Two short sentences, front-loaded with the core purpose and immediately followed by a differentiating clause. There is no filler, and every word contributes either to defining the match semantics or to distinguishing this tool from semantic search.

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 output schema, the description should explain what the tool returns, but it does not. It also omits how project and version filter results and how limit behaves. The tool is simple and read-only, but an agent would still need more context to invoke optional parameters correctly and interpret results.

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 compensate, but it only clarifies that pattern should be a known identifier. The optional parameters limit, project, and version receive no explanation of their meaning, defaults, or interaction, leaving a significant gap for correct invocation.

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 states a specific verb and resource: it performs an exact lexical match on a known identifier, and explicitly distinguishes itself from semantic ranking. It is clear that this is a precise lookup tool, though it does not name the underlying web3 resource being searched.

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 description implies usage for known identifiers requiring exact lexical matching, and the 'does not rank semantically' clause suggests it is not for fuzzy or semantic discovery. However, it never explicitly names an alternative such as web3_search or states when not to use this tool, so the guidance remains implied rather than directive.

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?

readOnlyHint is already true, so the safety profile is covered by annotations. The description adds a behavioral boundary: this is an exact typed-id lookup, not a search or ranking operation. It does not mention missing-ID behavior or result format, but that is a minor gap given the read-only annotation.

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?

Two short sentences deliver the main operation, the supported record types, and a key exclusion with no filler. The core information is front-loaded and every sentence 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?

The description adequately covers the core lookup semantics and one key behavioral boundary for a read-only tool. It is less complete on optional parameter semantics and return behavior, and since there is no output schema, those details are left to inference.

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?

The description adds meaning for the two required parameters: 'by id' explains the id field, and 'address, ABI, EIP' maps directly to the kind enum. With 0% schema description coverage, this is valuable, but chain, project, and version remain entirely unexplained.

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 names a precise operation (lookup by id) and a concrete resource set ('typed records: address, ABI, EIP'). The disclaimer 'Does not search prose or rank' clearly distinguishes it from the sibling search/grep tools.

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 'by id' phrasing implies this tool is for exact-record lookups when an identifier is known, and the 'Does not search prose or rank' sentence gives a useful exclusion. However, it does not explicitly name an alternative tool or state a direct 'use this when...' condition.

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?

The readOnlyHint annotation already establishes that this is a non-mutating operation, and the description adds meaningful behavioral detail beyond that: results are 'ranked selectors' and bodies are not returned. This is exactly the kind of extra context that helps an agent understand what to expect. There is no contradiction with the annotation.

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 two-sentence description is tightly written and front-loads the core purpose before adding the important exclusion. Every sentence contributes necessary information without filler. It loses a point for relying on jargon ('selectors') that is not defined and for omitting parameter guidance that could have been included in a compact list.

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 five parameters, no output schema, and four sibling tools, this description is too sparse to fully support correct invocation. It conveys the basic search behavior but leaves parameter semantics, result format details, and sibling routing unexplained. An agent would likely need to open schemas or 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?

With 0% schema description coverage, the description carries the full burden for parameter understanding, but it only hints that 'query' can be a prose phrase or an unknown identifier. The limit, intent, project, and version parameters are completely unexplained, leaving the agent to guess their roles. This is a significant gap for a 5-parameter tool.

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 clearly states the tool returns 'ranked selectors' for a 'prose query or unknown identifier,' which communicates the core search behavior and result form. The title adds the resource scope ('code and docs'), and the explicit 'Does not return bodies' helps distinguish it from a fetch operation. It could be stronger with a clearer verb like 'search' and explicit sibling differentiation.

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 phrase 'for a prose query or unknown identifier' gives useful context for when this tool is appropriate, and 'Does not return bodies' implicitly warns against using it when full content is needed. However, it never explicitly names sibling tools like web3_fetch, web3_grep, or web3_lookup or states when to prefer them. The guidance is implied rather than explicit.

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