mcp-reposkein

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

With no annotations, the description carries full burden. It discloses that the tool resolves identifiers, returns a neighborhood of calls with hops 1-2, includes an enrichment_needed list, returns candidates on ambiguity, and has a federated mode. It does not explicitly state read-only or destructive nature, but the description implies no mutations.

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?

Three sentences, each serving a clear purpose: core function, ambiguity handling, and federated option. No wasted words, information is front-loaded.

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?

No output schema, so description should clarify return structure. It mentions 'inlined prose and an enrichment_needed list' but does not detail the format or what other fields exist. Also missing error behavior (e.g., if target not found). Adequate but incomplete for a complex tool.

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 description must compensate. It explains that node_id, file_path+name, or name are three identification methods; hops can be 1 or 2; federated is for cross-repo traversal. This adds crucial meaning beyond the schema's bare type/constraint definitions.

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 it resolves a function/class by various identifiers and returns a caller/callee neighborhood with prose and enrichment list. It also notes it never guesses and returns candidates for ambiguity. While it distinguishes from siblings by focusing on dependency profiling, it does not explicitly differentiate from get_temporal_context or other siblings.

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 provides some guidance: use node_id, file_path+name, or name for identification; use federated:true for nested repos; never guesses but returns candidates for ambiguous names. However, it does not state when NOT to use this tool versus alternatives like impact or semantic_find.

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?

No annotations are provided, so the description must cover behavioral traits. It clarifies the tool is advisory (not authoritative) and derived from git history, but does not disclose potential performance implications or limitations (e.g., need for git history, staleness).

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 two concise sentences that front-load the key information (what it provides and the answer it gives), with no wasted words.

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 explains the tool's purpose and use case clearly but lacks details about output format or limitations (e.g., only works for files in git history). Given no output schema and no annotations, additional context would be beneficial.

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 should compensate for the 'path' parameter. It only implies it is a file path (via 'for a file'), but does not specify format, relative/absolute, or accepted file types, leaving ambiguity.

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 it provides git-derived signals for a file, including frequency, recency, ownership, and co-change, and answers 'what else should I touch?'. It distinguishes from siblings by focusing on temporal git signals, though not explicitly naming alternatives.

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 specifies usage before a cross-cutting change to find files that historically change together, providing clear context. However, it does not explicitly exclude when not to use or mention alternatives among siblings.

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?

No annotations, but description discloses split output, resolution by multiple identifiers, and federated behavior. Could add read-only hint but mutation is unlikely.

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 sentences: first explains core purpose, second adds resolution and federated flag. No fluff.

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?

Covers main purpose and many parameters, but depth parameter is missing. No output schema, so return format is vague ('impacted code vs tests' is high-level).

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 0%, but description explains node_id, file_path, name, and federated. Depth parameter not described, so not fully compensating.

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?

Description states 'return its transitive callers split into impacted code vs tests' which is a specific verb-resource pair. It also mentions resolution methods, differentiating from siblings like semantic_find.

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?

Implies use case: when changing a function/class to see impact and tests to run. Provides resolution methods but lacks explicit when-not-to-use or 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?

With no annotations, the description must carry the transparency burden. It discloses return value (node/edge counts) and states it uses a 'native indexer' and 'graph database,' but lacks details on destructiveness (rebuild overwrites), prerequisites, or performance implications.

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 concise with two sentences and no superfluous content. However, the lack of parameter documentation reduces the practical value for an agent, preventing a perfect score.

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 two undocumented parameters, the description does not provide enough detail for an agent to confidently invoke the tool. Important aspects like whether the 'full' boolean triggers a full index or incremental update are missing.

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%, yet the description provides no explanation of the two parameters 'path' and 'full'. This is a critical omission as agents cannot infer their purpose or correct usage from the description 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 indexes the repository and loads it into the graph database, differentiating it from sibling tools like reindex_file which operates on single files. It specifies the high-level action and resource, meeting the highest standard.

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 provides clear usage context: 'Run once on a fresh repo (or to rebuild).' It implies when to use (full repo indexing) and when not (single file changes suggest reindex_file), but does not explicitly name alternatives or state exclusion criteria.

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?

Discloses that writes are rejected and results are capped (200 rows / 64KB). No annotations provided, so description carries full burden; these are key behavioral traits beyond the schema.

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 concise sentences, each adding value: first states purpose and constraint, second provides usage patterns and limits. No wasted words.

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 no output schema or annotations, the description adequately covers purpose, usage, constraints, and parameter usage. Could mention return format or error handling but not required for completeness.

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 coverage, the description explains all three parameters (query, params, federated) and gives examples of how to use them (e.g., filtering by repo_id). Adds significant meaning beyond the bare schema.

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 uses 'Run a read-only Cypher query against the RepoSkein graph' which clearly states the action and resource. It distinguishes from siblings like 'write_semantic_summary' by emphasizing read-only and rejecting writes.

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?

Provides explicit guidance on filtering by repo_id and using federated flag to span repos. Does not explicitly state when not to use but implies for writes another tool is appropriate.

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?

No annotations are provided, so the description carries full burden. It discloses that v1 performs a 'full reindex', which implies a potentially expensive operation. However, it does not mention side effects, required permissions, or error conditions.

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 a single sentence that is front-loaded with purpose. It is concise but could be structured better (e.g., separate usage and behavior sections). Still, there is no wasted text.

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 one parameter, no output schema, and no annotations, the description is minimal. It does not explain what 'refresh the graph' means, whether the operation is idempotent, or how errors are handled. This leaves the agent with insufficient 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?

Schema coverage is 0%, and the description adds only 'pass its path' without clarifying path format (absolute/relative) or file existence requirements. For a single parameter, this adds negligible value beyond the schema's type definition.

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 verb 'Refresh the graph' (reindex) and resource 'source file' via path, and distinguishes from siblings like 'get_context_profile' or 'impact' by being the only tool for reindexing after editing. The mention of 'v1 performs a full reindex' adds specificity.

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 explicitly says to use 'after editing a source file' and to 'pass its path', providing clear context. However, it does not specify when not to use this tool or mention alternative 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?

With no annotations, the description carries full burden. It discloses the ranking behavior, the fact that it returns node_ids, and the federated scope. However, it does not explicitly state that the tool is read-only (no destruction), nor does it address authentication, rate limits, or error behavior. The description provides moderate 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 two sentences, front-loading the main purpose and mechanism. Every sentence adds value: first explains the ranking and purpose, second adds return type and federated detail. No wasted words.

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 the tool's complexity (4 params, no output schema, no annotations), the description covers main aspects: ranking mechanism, return type, usage context, and federated behavior. Lacks detail on output format of node_ids and explanation of all parameters (limit, kind), but overall adequate for a search tool with sibling 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?

Schema description coverage is 0%, so the description must compensate. It explains the 'query' parameter (used for lexical match) and 'federated' (spans nested repos), but does not explain 'limit' (though inferable) or 'kind' (enum meanings not described). Partial coverage, missing critical explanation for kind.

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 uses a specific verb ('Rank') and resource ('functions/classes'), explains the matching criteria ('lexical match over qualified names, signatures, and summaries'), and explicitly distinguishes from sibling tool 'get_context_profile' by positioning itself as the entry point. It also clarifies the return value ('ranked node_ids') and federated scope.

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 clearly states when to use the tool: 'the entry point to seed get_context_profile when you don't know where to start.' It provides context for the federated parameter and implies an alternative (get_context_profile) for subsequent use. However, it does not explicitly exclude scenarios where this tool should not be used.

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?

Describes staleness tracking via content hash and format restrictions, compensating for missing annotations. However, does not disclose error behavior or the effect of updating an existing summary.

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 sentences efficiently convey purpose, constraints, and behavior without wasted words. Front-loaded with the core action.

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 no annotations and no output schema, the description covers essential behavior and constraints. It could mention return value or error handling but is largely sufficient for a write tool.

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 coverage, the description adds meaning for 'summary' (plain text, length) but not for 'node_id' or 'model', which remain undefined. Partially compensates but leaves gaps.

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 attaches a 1-3 sentence plain-text summary to a node and distinguishes it from siblings like 'read_cypher' or 'semantic_find' by specifying the write action and business logic focus.

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 attaching summaries and provides constraints (plain text, max 1000 chars, 1-3 sentences), but lacks explicit guidance on when not to use or alternatives.

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