ejentum-mcp

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

With no annotations, the description carries the full burden of behavioral disclosure. It specifies the exact content returned (6 dimensions and failure modes), which is useful, but it does not explicitly state that the operation is read-only, that it takes no inputs, or any other operational trait beyond the implied read nature of 'List'.

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?

A single, front-loaded sentence that communicates the tool's output without any wasted words. Every part of the 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?

For a zero-parameter list tool with no output schema, the description adequately explains what will be returned. It could be more complete by clarifying when to choose this tool over siblings, but for the tool's complexity level it is largely sufficient.

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?

There are zero parameters, so per the rubric the baseline is 4. The description adds no parameter details because none exist, which is appropriate.

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 ('List') and a precise resource ('the 6 invariant cognitive failure dimensions and primary failure modes mapped by Ejentum'). An agent can tell what the tool returns, but the description does not distinguish it from sibling tools like ejentum_graph or ejentum_scaffold, so it falls short of a 5.

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 guidance on when to use this tool versus the sibling tools (ejentum_fts_search, ejentum_graph, ejentum_scaffold). The implied use is simply to list dimensions, but no conditions, exclusions, or alternatives are mentioned.

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 the full behavioral burden. It claims 'sub-millisecond' performance and BM25 ranking but says nothing about what a result contains, whether ranking scores are returned, whether access is read-only, or how results behave when there are no matches. With zero annotation coverage and no output schema, this is a significant gap for a search tool.

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?

A single tight sentence with the core purpose front-loaded. Nothing is redundant and no filler sentences pad it out.

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 two-parameter search tool with no output schema, the description conveys the corpus size (311 abilities) and the ranking approach, which is useful context. However, with no annotations and no explanation of return shape or failure behavior, it falls short of fully equipping an agent to invoke and interpret the 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 description coverage is 100%, so both parameters (query, limit) are already documented in the schema, making 3 the baseline. The description adds marginal value by framing query as keyword-based search rather than semantic, but it does not clarify the range/behavior of the limit parameter or query syntax beyond what the schema states.

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 specific verb (search) and resource (311 deterministic reasoning abilities) and specifies the mechanism (SQLite FTS5 keyword search with BM25 ranking). It does not differentiate itself from the sibling tools (ejentum_domains, ejentum_graph, ejentum_scaffold), so an agent cannot tell from the description alone why it would pick this over a graph or domain lookup.

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 explicit when-to-use guidance, no statement of when NOT to use it, and no reference to the sibling tools as alternatives. The only cue is the name and the phrase 'keyword search', from which the agent must infer that this is for literal term matching rather than semantic or graph traversal.

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 the full disclosure burden. It does reveal useful behavior — the graph's size (933 edges) and the shape of what it composes (a DAG built from four named operator types) — which implies a read-only traversal. But it omits cost/latency expectations, whether traversal is a read operation, and anything about determinism or failure modes, leaving meaningful gaps.

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?

A single sentence with no filler, and the core action plus output composition are front-loaded. It is efficient, though the density of undefined terms makes it harder to parse than a longer, clearer version would be.

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 and no annotations, the description is the only place an agent can learn what comes back, and it only partially delivers — naming the operator types but not the response structure, node/edge payload, or how depth changes the result. It is adequate at a minimum-viable level but thin for a 3-parameter, multi-hop traversal 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 description coverage is 100%, so the schema already documents depth (with its 1/2 enum semantics), query, and ability_id fully. The description adds nothing about parameter behavior beyond the schema, so the baseline 3 applies.

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 specific verb ('traverse') and resource ('933-edge cognitive synergy graph') and hints at the output ('multi-hop Cognitive DAG with Root, Prerequisite, Amplifier, and Fallback operators'). However, the jargon is never grounded — an agent cannot tell what a 'Cognitive DAG' actually is or does, and nothing distinguishes this from the sibling tools (ejentum_domains, ejentum_fts_search, ejentum_scaffold). Purpose is stated but 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?

There is no when-to-use guidance, no prerequisites, and no mention of any alternative. Three sibling tools exist that plausibly compete for the same query, yet the description never says when graph traversal is the right choice versus fts_search or scaffold.

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 the entire behavioral burden. It asserts 'deterministic', which is a genuine behavioral claim, but says nothing about what the tool returns, whether it mutates state, cost/latency, or how mode changes behavior.

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 front-loaded sentence with no padding or repetition, which is structurally sound. However, the length is spent on undefined marketing jargon rather than substantive information, so brevity does not translate into usefulness.

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 an abstract description, an agent has little to work with. It cannot tell what the scaffold output looks like, what each mode yields, or why it should choose this over its three siblings, leaving major gaps for a tool whose output shape is entirely undefined.

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 100%, with clear per-parameter text and a documented enum for 'mode', so the schema does the heavy lifting. The description adds no parameter meaning beyond what the schema already provides, which is the correct baseline of 3.

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?

It names a verb (retrieve) and a resource (a reasoning scaffold), so the general action is legible. But 'deterministic reasoning scaffold (Reasoning-Augmented Retrieval)' is proprietary jargon that never says concretely what comes back, and it draws no distinction from siblings like ejentum_graph or ejentum_fts_search.

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 gives no guidance on when to invoke this tool versus ejentum_domains, ejentum_fts_search, or ejentum_graph, nor any prerequisites or trigger conditions. The only implicit cue is the failure scenarios ('hallucinations, causal inversion'), which hint at intent but never frame a decision rule.

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