I2IDL Glossary of Digital Learning

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world semantics, so the safety profile is covered without prose. The description's only added behavioral value is naming what comes back (definition, references, metadata); it says nothing about missing-concept behavior, auth, or rate limits.

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 with no filler; verb and resource lead, payload follows. Nothing could be cut without losing information.

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 exists, but the description compensates by listing the returned fields, and annotations plus full schema coverage handle the rest. Only the absence of error/not-found behavior and sibling routing keeps it short of full 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?

Schema description coverage is 100% and the sole parameter is documented there as 'Canonical concept slug' with length bounds. The description adds no further meaning about the id format or lookup semantics, 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?

States a specific verb ('Retrieve') and resource ('glossary concept') and enumerates the payload (definition, references, metadata). It is distinguishable from search_concepts and get_relationships by resource type, but never explicitly contrasts itself with those 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?

No when-to-use guidance, no prerequisites, and no routing to alternatives. An agent must infer from the name and the required 'id' that this is a direct lookup rather than a search, with nothing telling it when to prefer get_concept over search_concepts.

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?

Annotations already establish the full safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds two genuine behavioral traits beyond the annotations: output is 'bounded' and 'citation-preserving', which tells the agent the return is size-limited and includes provenance. It does not explain what bounds apply or how citations are formatted.

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 with no redundant clauses. The trailing phrase 'suitable for grounding AI responses' is mildly marketing-flavored but does carry the intended use case, so it roughly 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 3-parameter read tool with annotations covering safety and a fully documented schema, the description is adequate but thin. With no output schema present, the description should give more shape to the returned 'bundle' (what it contains, how depth/maxRelated affect it) than a single adjective-laden phrase.

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% and each parameter carries its own inline description ('Canonical concept slug', '0 or 1 hop', 'Maximum neighbors'), so the schema already does the parameter work. The description adds no syntax or format detail beyond that, matching the baseline for fully documented schemas.

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?

States a specific verb ('Retrieve') and resource ('semantic context bundle') with two distinguishing attributes ('bounded', 'citation-preserving'). It is clear what the tool returns, but it never names or differentiates itself from the siblings get_concept, get_relationships, or search_concepts, so an agent must infer why 'context bundle' differs from a plain concept fetch.

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?

Usage is only implied by 'suitable for grounding AI responses', which hints at the scenario without stating when to prefer this over get_concept or search_concepts. No exclusions or preconditions (e.g., that id must be a known concept slug) are given.

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?

Annotations already declare this as a safe, read-only, idempotent operation, so the description need not restate safety. It adds useful context by specifying that the output includes broader, narrower, and related concepts with canonical identifiers, but it does not describe return format, pagination, error behavior, or any constraints beyond what annotations provide.

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 front-loaded sentence with no filler. Every word contributes to stating the tool's purpose and output content.

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 simple one-parameter read operation, full annotation coverage, and the absence of an output schema, the description adequately conveys the return content (relationship types and identifiers). It could be slightly more complete by mentioning any limitations, such as behavior when the concept has no relationships, but the core information an agent needs is present.

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%, and the single parameter is documented as "Canonical concept slug" in the schema. The description adds no additional meaning beyond the schema, which is the expected baseline when the schema itself is fully documented.

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 gives a specific verb ("Retrieve") and a precise resource ("broader, narrower and related concepts with their canonical identifiers"), so an agent can tell this is about fetching relationships rather than concept details. However, it does not explicitly distinguish itself from siblings like get_concept or get_context, so it falls short of full 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 description states what the tool returns but offers no guidance on when to use it versus alternatives such as get_concept or search_concepts. There is no mention of prerequisites, exclusions, or contexts that should trigger this tool over its 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful context by disclosing the return content (identifiers and canonical URLs). It says nothing about rate limits, auth requirements, or matching/ranking behavior, so it adds moderate value beyond the annotations.

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 zero filler, front-loading the verb and resource and appending the return contract. Every clause 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 output schema, the description usefully states what the tool returns (identifiers and canonical URLs) and the parameters are fully documented in the schema. The remaining gap is routing guidance against the three sibling tools, which is left implicit.

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 the query text and the 1-20 limit are already documented in the schema. The description adds no syntax, matching-mode, or formatting detail beyond that baseline.

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?

States a specific verb (Search) and resource (published I2IDL glossary concepts), and even names what is returned (identifiers and canonical URLs). It does not explicitly distinguish itself from the get_concept sibling, so an agent must infer that this is the lookup/find operation while get_concept retrieves a single concept by ID.

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 when-to-use guidance, no statement of when-not to use it, and no reference to the available alternatives (get_concept, get_context, get_relationships). Usage is only implied by the verb 'Search'.

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