elsa-agent-gateway

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

Annotations mark the tool as read-only (readOnlyHint: true), but the description claims it 'te lleva a unirte' (takes you to join), implying a possible side effect. This creates an ambiguity about whether the tool actually performs a join action or merely navigates. The description does not clarify the behavioral boundary 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?

The description is a single concise sentence that front-loads the core purpose. However, it could be more structured to separate the recommendation from the navigation step.

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 is provided, and the description does not explain what the tool returns (e.g., a club recommendation, a link, or something else). The tool has 3 parameters and moderate complexity, but the description omits the output format and any post-recommendation behavior.

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 descriptions exist for location and weekly_volume_km, but preferred_days lacks description in both schema and tool description. The description only mentions 'volumen y zona', not preferred_days, providing no additional semantic value beyond the 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 clearly states the tool recommends a cycling club based on volume (weekly_volume_km) and zone (location), and guides the user to join and confirm a first ride. It distinguishes from the sibling tool 'plan_my_block' which likely plans training blocks.

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 guidance on when to use this tool versus alternatives. No comparison with sibling tool 'plan_my_block' or conditions under which it 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?

The annotations declare readOnlyHint=true and openWorldHint=false. The description adds that the tool returns a periodized block with readiness and leads to activation. This provides useful behavioral context beyond annotations, though the activation aspect could be clarified whether it triggers state changes or just provides a link. No direct contradiction; the description enriches understanding.

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 efficiently conveys purpose, outcome, and next step. It is front-loaded with the key action. Could be slightly more structured (e.g., bullet points) for readability, but no extraneous 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 schema (3 params, no enums, no nested objects), the presence of read-only annotations, and no output schema, the description adequately explains what the tool does and its outcome. It does not detail return format, but the tool's purpose is clear. Sibling context helps. Minor gap: no explicit mention of parameter roles, but schema fills that.

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 100% with descriptions for all 3 parameters. The description does not explicitly detail parameters but relates 'goal_event' and 'event_date' to the training block context. It omits 'recent_training' but that is optional. Since the schema already provides adequate parameter semantics, the description adds only marginal context, meeting the 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?

The description clearly states the tool returns a periodized cycling training block (base/build/peak/taper) for a goal event with a readiness verdict and leads to activation in ELSA. This distinguishes it from the sibling 'match_me_a_club' which is about club matching.

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 implied (for planning a training block towards an event), but there is no explicit guidance on when to use it vs alternatives. No mention of prerequisites or exclusions. The sibling tool serves a completely different purpose, so confusion is minimal, but direct guidance is missing.

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