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

Annotations already declare it read-only, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: it discloses the authentication mechanism (user's bearer token forwarded upstream) and enumerates the response fields (marker slug, kind, severity, trend/year, sample count, date range, headline, detail). Only error/pagination behavior is left unstated.

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?

Front-loaded with the purpose, then the response shape, then the proxy/auth detail — a logical order. The field enumeration is long but justified because there is no output schema; no sentence is filler, though the sentence count could be trimmed slightly with list formatting.

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 carries the return-value burden and does so by listing the key fields; auth requirements are disclosed and the upstream endpoint is named. Minor gaps are absence of empty-result behavior and upstream error handling, but nothing an agent needs to invoke the tool correctly is 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 100%, so the single bearer_token parameter is already fully documented, including how to obtain it. The description still adds meaning by explaining what the tool does with the token — forwards it as 'Authorization: Bearer' to the upstream trajectory endpoint — which the schema alone does not say.

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 and resource ('Return the per-marker trajectory analyser output') with scope ('authenticated patient') and concrete examples (HbA1c rising, eGFR falling, ferritin depleting). This clearly distinguishes it from siblings like explain_marker, lookup_marker and get_patient_history, which explain a marker or fetch history rather than computing per-marker trends.

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 usage context is only implied — it is for the authenticated patient and proxies a specific trajectory endpoint — but there is no explicit 'use this when...' or exclusion against get_patient_history or explain_marker. An agent can infer it yields trend warnings, but has to reason about the alternative itself.

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