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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=false, so the safety profile is covered. The description usefully adds that scopes accept wildcards and that budget_minor is a total spend ceiling, plus that a covenant_id is returned. It does not disclose authorization requirements, what happens when a matching covenant already exists (relevant given idempotentHint=false), or any failure modes.

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 compact sentences, front-loaded with the core definition followed by the parameter semantics an agent most needs. The trailing "Returns the covenant_id" is slightly redundant given an output schema exists, but the sentence is short and cheap.

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 five-required-parameter authority-granting mutation with no schema descriptions, the definition is adequate but not complete: it covers scope, budget and expiry semantics while leaving principal/agent_id and the authorization model unstated. The output schema means return values need not be explained, so that gap is not held against it.

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 carry the parameter meaning, and it does explain three of five: scopes wildcard syntax with concrete examples, budget_minor as a total spend ceiling in minor units, and expires_at as ISO-8601. The two most semantically load-bearing fields, principal and agent_id, are left entirely to inference from the phrase "grant an agent".

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?

Names a specific verb and resource ("Grant an agent a covenant") and defines the resource as "an explicit lease of authority", which is far more informative than the title alone. It is clearly distinguishable from revoke_covenant, list_covenants and covenant_status, though it never names those siblings explicitly.

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 by the verb plus the resource definition, so an agent can infer this is the creation path for a covenant. There is no explicit when-to-use/when-not-to-use guidance, no mention of the sibling revoke_covenant as the inverse operation, and no stated prerequisites (e.g. whether the caller must be the principal).

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